Python · ★ 6,415 · 🍴 452 · 📈 1,265 stars today
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
中文介绍 针对大语言模型应用成本问题，headroom 是一个前置压缩工具，能在数据（如工具输出、日志、RAG 上下文）进入 LLM 前进行智能压缩，可减少 60-95% 的 token 消耗且不损失答案质量。它提供库、代理和 MCP 服务器三种集成方式，适用于需要优化 RAG 管道或处理大量输入数据的开发者。
Python · ★ 141,143 · 🍴 9,614 · 📈 3,618 stars today
Python tool for converting files and office documents to Markdown.
中文介绍 微软推出的 Python 工具 MarkItDown，专注于将各类文件和 Office 文档（如 PDF、Word、PPT）高效转换为 Markdown 格式。这对于构建知识库、文档处理流水线或进行文本分析的开发者非常实用，能简化非结构化数据的标准化过程。
JavaScript · ★ 203,959 · 🍴 31,292 · 📈 1,533 stars today
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
中文介绍 ECC 是一个面向 AI 智能体的性能优化系统，旨在增强如 Claude Code、Codex、Cursor 等 AI 编程助手的能力。它通过技能库、直觉机制、记忆管理和安全架构等模块，采用研究先行的开发模式，提升智能体在复杂任务中的表现与安全性。
Python · ★ 59,175 · 🍴 5,718 · 📈 1,182 stars today
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
中文介绍 Scrapling 是一个自适应的 Python 网络爬虫框架，能够灵活处理从单次简单请求到大规模全站爬取的各种场景。它设计用于应对复杂的现代网站，内置反反爬策略，适合需要稳定、高效获取网络数据的数据工程师和研究人员。
Python · ★ 12,543 · 🍴 1,540 · 📈 1,722 stars today
Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!
中文介绍 Hermes WebUI 是 Hermes Agent 的官方 Web 界面，提供了通过浏览器或手机便捷访问和使用 Hermes AI 智能体的途径。它让非技术用户也能轻松利用 Agent 的功能，适用于需要在移动端或协作环境中进行 AI 交互的场景。
TypeScript · ★ 4,509 · 🍴 582 · 📈 124 stars today
A modern platform for visual, flexible, and extensible graph-based investigations. For cybersecurity analysts and investigators.
中文介绍 Flowsint 是一个面向网络安全分析师和调查员的现代调查平台，支持基于图的可视化分析。它允许用户以灵活、可扩展的方式构建和关联调查节点，适用于威胁情报分析、事件响应和数字取证中处理复杂关联数据的场景。
Python · ★ 25,116 · 🍴 2,881 · 📈 783 stars today
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
中文介绍 VoxCPM2 是 OpenBMB 开源的文本转语音系统，其特点是无需分词器，支持多语言语音生成、创造性声音设计以及高保真声音克隆。它为有声读物、语音助手、个性化语音内容创作等场景提供了高质量、可控的语音合成解决方案。
Jupyter Notebook · ★ 18,462 · 🍴 5,225 · 📈 574 stars today
Code for Machine Learning for Algorithmic Trading, 2nd edition.
中文介绍 该项目是《算法交易机器学习》（第二版）一书的配套代码库。它系统性地展示了如何将机器学习技术应用于量化交易策略开发、特征工程、模型构建和回测，是金融工程和量化研究员学习与实践的实用资源。
Python · ★ 6,376 · 🍴 1,488 · 📈 30 stars today
中文介绍 这是一个专注于生产环境 Agentic RAG（检索增强生成）的实战课程。它旨在帮助开发者系统学习如何构建、部署和维护具备智能体特性的、可投入生产的 RAG 系统，解决从原型到生产落地的工程化挑战。
TypeScript · ★ 24,629 · 🍴 2,179 · 📈 680 stars today
Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.
中文介绍 SuperMemory 是一个为 AI 时代设计的超快速、可扩展的记忆引擎与应用。它提供 Memory API，旨在解决大语言模型缺乏长期、个性化记忆的痛点，适用于需要为 AI 助手或应用构建持久化、高效检索记忆层的开发者。
Python · ★ 8,355 · 🍴 1,074 · 📈 66 stars today
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms
中文介绍 Open-LLM-VTuber 允许用户通过免提语音与任何大语言模型进行对话，并支持语音打断和驱动 Live2D 虚拟形象，且完全本地化运行。它为 VTuber 主播、虚拟助手开发者提供了低成本、高隐私的交互式 AI 虚拟角色集成方案。
@elpresidank · 116 粉丝 · 2.9M 阅 · 543 赞 · 35 转
Most AI agent memory is built on embeddings. And there's now a proof that this entire class of system is going to forget what you stored in it — and confidently make up things you never stored at all.
中文介绍 AI代理内存多基于嵌入系统，新证明该类系统会遗忘存储内容并自信编造未存信息。博主提出用拓扑结构替代，防止信息丢失，为代理内存设计提供理论框架和解决方案。
@1salman · 363 粉丝 · 2.0M 阅 · 682 赞 · 45 转
Everyone keeps asking whether AI favors specialists or generalists. I think that is the wrong question. AI does not pick a side. It changes the tradeoff. The old world forced a choice. You could go
中文介绍 AI并非偏好专家或通才，而是改变了二者间的权衡。旧模式迫使专业与通用二选一，现在可按需获取范围与深度，为人才策略和职业发展提供新视角。
@eng_khairallah1 · 61.9K 粉丝 · 693.5K 阅 · 511 赞 · 71 转
Obsidian has 2,700+ community plugins. Over 100 of them are AI-related. Save this :) And the CEO of Obsidian personally published official Claude Skills for the platform - 12,900+ GitHub stars in
中文介绍 分享Obsidian的30个隐藏工作流、插件和设置，涉及2700多社区插件中100多个AI相关项。CEO发布官方Claude Skills，获12900+ GitHub stars，助力知识管理和AI集成。
@prukalpa · 23.1K 粉丝 · 583.2K 阅 · 506 赞 · 80 转
A field guide to what it is, what it is not, and where it fits in your AI architecture. I have had some version of the same conversation with a CIO almost every day this year. Their team has read
中文介绍 企业上下文层的实操指南，厘清其定义、边界及在AI架构中的角色。通过与CIO的日常对话，解决团队困惑，推动上下文层在实践中的正确应用和优化。
@theonejvo · 22.1K 粉丝 · 504.3K 阅 · 861 赞 · 1 转
Over the past year, @pewdiepie, has been turning into one of the most visible champions of private, self-hosted computing, and it has been a genuine pleasure to watch. What began in late 2025 as an
中文介绍 展示如何入侵pewdiepie的AI代理harness，通过恶意cocomelon网站测试安全漏洞，随后协助加固防护。案例突显AI代理安全挑战与私有自托管计算的重要性。
@monokern · 1.2K 粉丝 · 263.1K 阅 · 505 赞 · 72 转
Most people treat research as a manual task. You open 10 tabs. You watch videos. You read articles. You take notes somewhere. An hour later you have a pile of information you're not sure what to do
中文介绍 结合Claude Code、NotebookLM和Obsidian打造智能研究系统，自动处理多标签页、视频和文章，随使用次数提升智能。将手动研究任务转为持续优化的自动化工作流。
@garrytan · 853.3K 粉丝 · 180.6K 阅 · 503 赞 · 43 转
In January I got back into coding and I built Garry's List. Over five hundred thousand lines of Rails and the tests to police it. I was proud of it. I shouldn't have been. The thing worth being proud
中文介绍 博主构建Garry's List超50万行Rails代码，但反思不应自豪。强调代理开发中避免过度工程（“福克斯康工厂”），聚焦核心价值和简洁设计。
@dair_ai · 124.6K 粉丝 · 84.0K 阅 · 504 赞 · 83 转
1. SkillOpt Microsoft Research treats a compact natural-language skill document as the trainable state of a frozen agent, then learns that document through rollouts, reflection, and bounded edits
中文介绍 本周顶级AI论文摘要，重点介绍SkillOpt。微软研究院将自然语言技能文档作为冻结代理的可训练状态，通过滚动、反思和有限编辑学习，提升代理技能和适应性。
@trq212 · 263.1K 粉丝 · 75.7K 阅 · 542 赞 · 36 转
Last week, we released dynamic workflows in Claude Code. Claude can now write its own harness on the fly, custom-built for the task at hand. While the default Claude Code harness is built for coding,
中文介绍 Claude Code推出动态工作流，允许Claude根据手头任务即时生成专属harness。不同于固定编码环境，此功能让代理更灵活，增强任务适应性和执行效率。
@mvanhorn · 27.6K 粉丝 · 54.5K 阅 · 545 赞 · 44 转
Three months ago I posted "Every Claude Code Hack I Know." It hit 913K views. @kevinrose had asked what IDE to use, and my answer was: "No IDE. Just plan.md files and voice." This used to be called
中文介绍 汇总所有代理工程技巧，基于先前913K浏览量的帖子。强调无IDE方法，使用plan.md文件和语音控制Claude Code，提升开发效率和交互体验。
@0xJeff · 80.5K 粉丝 · 47.0K 阅 · 512 赞 · 45 转
It’s been a little more than 2 months now and Hermes has taught me so many different things. One of the key things is that Agents like Hermes or OpenClaw don’t fail on intelligence, they tend to fail
中文介绍 使用Hermes Analyst 60天，分享6个工作流和6个教训。关键发现：代理如Hermes或OpenClaw失败常因工程问题而非智能不足，需优化工作流设计。
GitHub pioneered the modern AI coding era with Copilot, and the resulting explosion in agentic coding has led to notable strains on the most popular developer platform in the world. Here's the plan.
中文介绍 GitHub首席运营官Kyle Daigle介绍了公司的AI代理计划。该计划旨在应对因Copilot引领的AI编码时代带来的挑战，特别是代理式编码对GitHub这一全球最热门开发者平台造成的压力。
中文介绍 Hugging Face发布Holo3.1模型，该模型旨在为计算机使用场景提供快速且本地的AI代理功能。
Travelers built an AI-powered Claim Assistant with OpenAI to guide customers through filing claims, provide 24/7 support, and scale operations during peak demand.
中文介绍 Travelers保险公司与OpenAI合作，部署了AI驱动的理赔助手，以引导客户提交索赔、提供全天候支持，并在需求高峰期扩展业务。
The global health care sector is under increasing strain. Decades of chronic underinvestment and constraints in recruitment have coincided with a surge in demand for services for aging populations. Gaps in provision are already taking a toll, with fragmented access to care and high rates of stress a
中文介绍 全球医疗系统面临长期投资不足、招聘受限与老龄化人口需求激增的双重压力。代理式AI技术被视为一种途径，有望通过自动化等手段缓解医疗资源碎片化等问题，从而改善服务。
Discover new Codex plugins, sites, and annotations that help analysts, marketers, designers, investors, and other teams get more done with AI.
中文介绍 OpenAI发布了面向分析师、营销人员、设计师、投资者等多种角色的Codex新插件、站点和注解，旨在帮助不同团队利用AI提升工作效率。
This article is from Making AI Work, MIT Technology Review’s limited-run newsletter examining how to apply LLMs across industries. To receive it in your inbox,sign up here. From accounting to design to market research and product development, there’s a staggering breadth of skills needed to run a bu
中文介绍 本指南探讨小型企业如何应用大型语言模型（LLMs），范围涵盖从会计、设计到市场调研和产品开发等广泛技能领域。
OpenAI calls for global action on youth AI safety, proposing an international institute to strengthen safeguards, standards, and opportunities for young people.
中文介绍 OpenAI呼吁全球在青年AI安全方面采取行动，提议建立一个国际机构，以加强保障措施、制定标准，并为年轻人创造更多机会。
Jensen scores a huge win.
中文介绍 据Latent Space报道，NVIDIA发布了Cosmos 3、Nemotron 3 Ultra以及RTX Spark等新品。该报道指出这被视为公司CEO黄仁勋（Jensen）取得的一次重大胜利。
The Next Era of Knowledge Work report explores how Codex is transforming productivity through AI-powered research, data analysis, workflow automation, and content creation.
中文介绍 《知识工作新时代》报告阐述了Codex如何通过AI驱动的研究、数据分析、工作流自动化和内容创作，正在转变知识工作的生产力。
中文介绍 TLDR AI的日报新闻标题包括：Anthropic提交IPO申请、OpenAI服务登陆亚马逊AWS平台，以及Perplexity搜索代码等信息。
Our approach to AI policy and political advocacy, transparency, support for thoughtful regulation and AI safety, and that no outside political group speaks on the company’s behalf.
中文介绍 OpenAI阐述了其在AI政策与政治倡导方面的立场，强调透明度、支持深思熟虑的监管及AI安全，并声明没有任何外部政治团体可以代表该公司发声。
中文介绍 JetBrains在Hugging Face上发布其120亿参数的混合专家（MoE）模型Mellum2。
Inside xAI: Building Grok Imagine in 3 Months, Videogen vs World Models, and why Grok Imagine is so underrated. For the first time, we do a deep dive with the guy who led it!
中文介绍 xAI工程师Ethan He领导了Grok Imagine的开发。文章探讨了视频生成代理模型为何是下一个趋势，并深入分析了其开发过程、与世界模型的对比以及该产品的潜力。
中文介绍 IBM研究在Hugging Face发表文章，探讨超越大型语言模型（LLMs）的议题，指出企业AI的规模化采用依赖于代理逻辑（Agent Logic）。
OpenAI breaks ground on a 1GW data center project in Michigan as part of Stargate, building AI infrastructure to expand access, create jobs, and support communities.
中文介绍 OpenAI在密歇根州为其Stargate项目破土动工，建设一个1吉瓦（GW）的数据中心，旨在扩建AI基础设施，以扩大访问、创造就业并支持当地社区。
第一作者: Bardia Mohammadi · 方向: 密码学协议
幽灵工具调用推测性工具隐私语言代理隐私合约延迟隐藏
Abstract:Tool-augmented language agents speculatively issue likely future tool calls to hide latency, but those calls leak inferred user intent to external services before the agent commits to the branch. Every external observer that received the call retains the disclosure after the agent abandons the branch. Timing is the issue, not authorization: no commit-time cleanup, read-only restriction, or access-control allow-list unsends what an observer already holds. We call these invocations ghost tool calls and propose Speculative Tool Privacy Contracts, a runtime abstraction that treats observation before commitment as a first-class effect, distinct from state mutation. We implement the contracts in a prototype runtime and evaluate twelve policies across three corpora. Speculative dispatch increases what an observer can infer about user intent; post-hoc filters, read-only restrictions...
论文介绍 工具增强的语言代理为隐藏延迟而推测性发出工具调用，但这会在代理提交前泄露用户意图给外部服务，形成幽灵工具调用。本文提出推测性工具隐私合约，一种运行时抽象，将承诺前的观察视为一等效应，旨在解决工具调用中的时间隐私问题。该方法可用于保护代理工具调用的隐私，防止意图泄露。
第一作者: Elia Onofri · 方向: 密码学协议
无意传输物联网设备二次剩余问题密码学协议客户端优化
Abstract:Oblivious Transfer (OT) is a fundamental cryptographic primitive enabling privacy-preserving computation and constitutes a core building block for secure multi-party computation while supporting a wide range of security-sensitive applications: private information retrieval, zero-knowledge proofs, and password-authenticated key exchange, to cite a few. While recent advances in OT extension have significantly reduced amortised costs, their reliance on batches of random base OTs and substantial pre-computation phases limits their practicality in scenarios where the number of transfers is modest or where communication latency and client-side computation are critical constraints. In such settings, efficient base OT protocols remain both relevant and necessary. In this work, we introduce $I$-$(OT)^2$, a novel base 1-out-of-2 OT protocol grounded in the quadratic residuosity problem...
论文介绍 无意传输是隐私保护计算的基础原语，但现有扩展在IoT设备等场景中因预计算和通信延迟而不实用。本文提出I-(OT)^2协议，一种基于二次剩余问题的基础1-out-of-2无意传输协议，针对客户端计算和延迟优化。该协议可能应用于资源受限环境中的安全多方计算和私有信息检索。
第一作者: Hao Cheng · 方向: AI 安全
自主代理安全评估规范驱动任务合成大语言模型代理
Abstract:Autonomous LLM agents increasingly operate in stateful environments where they access tools, files, memory, and external services. While such capabilities enable complex real-world workflows, they also introduce security risks that are difficult to capture with existing evaluations. Current agent security benchmarks often rely on manually curated tasks, provide limited coverage of emerging threats, and focus primarily on final outcomes rather than the execution processes that lead to unsafe behavior. We introduce SeClaw, a framework that combines specification-driven security task synthesis with execution-based security evaluation for Autonomous agents. Spec-driven security task synthesis enables scalable and controllable construction of security tasks from structured risk specifications, while SeClaw docker provides a standardized testbed for evaluating agent behavior under...
论文介绍 自主LLM代理在有状态环境中操作，引入安全风险，但现有基准覆盖不足且关注结果而非过程。本文提出SeClaw框架，通过规范驱动合成安全任务，并基于执行评估代理行为，旨在提升安全评估的可控性和覆盖范围。该方法可用于测试和增强代理的安全性，应对新兴威胁。
第一作者: Hiskias Dingeto · 方向: AI 安全
大语言模型代理红队测试间接提示注入软件即服务集成安全基准
Abstract:Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls. Existing benchmarks under-measure the threat: most cover only a handful of integrations with the same attack payload replayed across runs, and open-source guards are trained on chat-style data rather than tool-response content. We introduce AGENTREDBENCH, a dynamic LLM-driven redteaming benchmark of 215 subtle underspecified authorization (attacks at the boundary of what the user's request authorises) scenarios across 24 enterprise integrations in nine functional families and five attack types. Across an eight-model panel (Anthropic, OpenAI, Google), no-guard ASR (attack success rate) ranges from 32% (Claude Sonnet 4.6) to...
论文介绍 LLM代理从SaaS集成中读取内容，面临间接提示注入威胁，但现有基准覆盖有限且负载单一。本文引入AgentRedBench，一个动态红队测试基准，包含215个场景跨24个企业集成，评估代理在多种攻击类型下的安全性。该基准可用于代理防御策略的测试和优化。
第一作者: Meng Wang · 方向: 软件安全
Python安全恶意软件分析强制执行引擎程序分析供应链安全
Abstract:The rapid expansion of the Python ecosystem has fueled two distinct but converging threats: adversaries increasingly target the software supply chain via the Python Package Index (PyPI), while also building evasive, cross-platform malicious binaries compiled from source code written in Python. Current program analysis techniques struggle to address this dual threat. Static analysis based tools are often blinded by runtime obfuscation and compiled bytecode, while dynamic analysis based ones are fragile, prone to evasion by environmental guardrails, and often terminates prematurely due to unsatisfied dependencies. To overcome these limitations, we present PyFEX, a resilient forced-execution engine. PyFEX explores a program's behavioral space systematically by forcing execution across all conditional branches to bypass evasion checks. To address the fragility of dynamic...
论文介绍 Python生态中的规避性恶意威胁通过混淆和环境防护逃避现有分析工具。本文提出PyFEX，一个弹性强制执行引擎，通过系统探索所有条件分支来绕过规避检查，揭示程序行为。该引擎可用于检测恶意Python包和二进制文件，增强软件供应链安全。
第一作者: Ahto Buldas · 方向: 区块链安全
Unicity框架谓词原子交换区块链链下计算
Abstract:We generalize Unicity token ownership to programmable spending conditions called predicates, enabling smart-contract like functionality executed off-chain directly by relying parties rather than by consensus participants. We prove that the security properties of the Unicity execution layer are preserved under reduction to predicate family unforgeability. To demonstrate the utility of the model, we show how to implement trustless atomic swaps by using predicates.
论文介绍 本文将Unicity代币所有权扩展到可编程谓词条件，支持链下智能合约功能。通过证明谓词家族不可伪造性确保安全属性，并展示如何实现无信任的原子交换。该方法可能应用于区块链中的去中心化金融和跨链交易，提升灵活性。
第一作者: Ahto Buldas · 方向: 密码学协议
Unicity执行层链下交易防双花隐私保护数字签名
Abstract:This paper introduces the Unicity Execution Layer, a modular component of the Unicity framework enabling secure off-chain transactions while maintaining trustless double-spending prevention. We present a formal security model where token ownership is represented by public keys and transfers require digital signatures. We prove three fundamental security properties: (1) no double-spending--each token state can be spent at most once, (2) no blocking--only the legitimate owner can prevent a token from being spent, and (3) service-side privacy--the Unicity Service cannot link transactions with the same token. The user-side privacy is addressed by introducing generalized multi-public-key signature schemes that allow one secret to generate multiple unlinkable public keys, and interactive and non-interactive concrete instantiations, enabling private transactions with stable public...
论文介绍 为实现在区块链上安全隐私的链下交易，本文提出Unicity执行层，一个模块化组件，通过形式安全模型和多公钥签名方案确保防双花、无阻塞和隐私。该执行层可用于扩展区块链性能，支持私密交易，适用于隐私敏感应用。
第一作者: Alvin Charles · 方向: 软件安全
二进制模糊测试静态二进制重写程序分析漏洞检测闭源软件
Abstract:Binary-only fuzzing is a key technique for finding bugs in close-source software. Without access to source code, the fuzzer must rely on static or dynamic binary instrumentation for coverage guidance. In practice, most fuzzers favor dynamic binary instrumentation (DBI), accepting runtime overhead to avoid the perceived accuracy and soundness challenges associated with static binary instrumentation (SBI). We show that these concerns are unwarranted, and that accurate, scalable~SBI is achievable using off-the-shelf frameworks. Building on these frameworks, we develop PeAR, an extensible binary-only fuzzing framework. We demonstrate PeAR's versatility by implementing several modern fuzzer features -- including, deferred initialization, persistent mode, and shared-memory fuzzing. We evaluate PeAR over 4.25 CPU-yrs of fuzzing on the FUZZBENCH benchmark and find that PeAR: (i)...
论文介绍 纯二进制模糊测试在闭源软件中查找漏洞，但动态仪表化有开销，静态仪表化被感知为挑战。本文提出PeAR框架，基于静态二进制重写实现准确、可扩展的覆盖指导，并支持现代模糊器特性。该框架可用于提升二进制模糊测试的效率和漏洞发现能力。
第一作者: Vu Minh Chau · 方向: 密码学协议
后量子密码学HQC解码向量优化NPU集成设备Hexagon处理器
Abstract:Hamming Quasi-Cyclic (HQC) has been selected by NIST for standardization as an additional code-based key-encapsulation mechanism, providing algorithmic diversity alongside lattice-based post-quantum cryptography. Efficient deployment of HQC on mobile and embedded platforms, however, requires careful optimization of its decoding procedure, whose Reed-Muller and Reed-Solomon components dominate the computational cost. This paper studies HQC decoding on Qualcomm Hexagon processors in NPU-integrated devices, focusing on the Hexagon Vector eXtensions (HVX) backend rather than a tensor-inference engine. We observe that HQC decoding naturally exposes vector-structured computation, including Reed-Muller reliability vectors, Hadamard-transform coefficients, Reed-Solomon syndrome vectors, finite-field products, and packed support-point evaluations. Based on this observation, we redesign...
论文介绍 HQC作为NIST选定的后量子密码标准之一，其高效的移动与嵌入式部署面临挑战，尤其是解码过程中Reed-Muller和Reed-Solomon组件的高计算成本。本文研究在集成NPU的高通Hexagon处理器上，利用Hexagon向量扩展（HVX）优化HQC解码过程。研究发现解码计算具有天然的向量结构，据此重新设计了核心算法，以利用HVX的并行处理能力，旨在提升资源受限设备上的后量子密码解密性能。
第一作者: Yani Wang · 方向: 系统安全
多模态大语言模型越狱攻击分布式语义重组AI安全跨模态攻击
Abstract:Multimodal Large Language Models (MLLMs) have recently demonstrated remarkable capabilities in content synthesis and autonomous reasoning. Previous safety guardrails are primarily designed for unimodal textual input interception, leaving them vulnerable to cross-modal jailbreak attacks. However, regardless unimodal textual attack or cross-modal jailbreak, typically inclusive part of explicit harmful or sensitive content at the input level, which is called Harm-Bearing. It allow the model's safety filters to detect and block such content easily. To address this limitations, we propose Distributed Semantic Recomposition (DSR), a novel cross-modal jailbreak framework that decomposes harmful intent into a set of benign textual and visual primitives. By exploiting the model's reasoning ability, DSR enables the latent fusion of these seemingly innocent components into harmful...
论文介绍 多模态大语言模型的安全防护主要针对文本输入，对跨模态越狱攻击防御不足。现有攻击通常在输入中包含显式的有害内容，容易被检测。本文提出「分布式语义重组」框架，通过将有害意图分解为一组看似良性的文本与视觉基元，再利用模型的推理能力，使这些无害组件在模型内部融合成有害输出。该方法揭示了当前安全机制在过滤隐式跨模态语义组合方面的漏洞。
第一作者: Ray Iskander · 方向: 区块链安全
智能合约安全重入攻击形式化验证Lean 4OpenZeppelin
Abstract:We present the first machine-checked correctness proof of the OpenZeppelin reentrancy-guard pattern against a Lean 4 state-machine model of production-deployed Solidity source. All thirteen theorems are machine-checked with zero sorry, zero user-introduced axioms, and an axiom footprint bounded by [propext] (a standard mathlib4 axiom), gated under continuous integration. Smart contract reentrancy has caused over US$500M in documented losses since 2016, with the DAO 2016 attack draining ~3.6M ETH and forcing the hard fork that split Ethereum. The OpenZeppelin ReentrancyGuard pattern is the de facto defense across production DeFi, yet no prior work has established its discriminating power: that the guard blocks attacks on vulnerable instances, preserves correct execution for non-attacking transactions, and distinguishes adjacent safe and vulnerable variants. Prior efforts...
论文介绍 智能合约重入攻击已造成巨大经济损失，OpenZeppelin的重入防护模式是事实标准，但此前缺乏严格的形式化验证。本文首次使用Lean 4对部署在生产环境中的Solidity源代码的重入防护模式进行了机器检查的正确性证明。该证明严格验证了该防护模式能够阻止攻击、保留正常执行并区分安全与脆弱变体，所有定理均通过机器检查，无外部假设，提升了该关键安全组件的可信度。
第一作者: Eric Liang · 方向: AI 安全
分布式事件系统安全监控混合AI/ML异常检测访问控制
Abstract:Distributed event-based systems have become a common substrate for Internet-scale publish/subscribe services, IoT telemetry, cloud-native microservices, and security operations pipelines. Their loose coupling and asynchronous delivery improve scalability, but they also expand the attack surface: publishers, brokers, subscribers, topics, schemas, and temporal ordering can each be abused without a single component observing the whole behavior. This paper proposes SECUREVENT, a hybrid AI/ML security-monitoring architecture for distributed event-based systems. The architecture combines traditional protections such as authenticated transport, topic-level authorization, and signed events with online anomaly detection, graph-aware behavioral features, complex-event policy rules, federated learning, and adversarial-ML governance. A deterministic prototype study over synthetic...
论文介绍 分布式事件系统因其松耦合特性被广泛应用，但也扩大了攻击面。本文提出SECUREVENT，一种混合AI/ML安全监控架构。该架构结合了传输认证、主题级授权、事件签名等传统保护措施，以及在线异常检测、图感知行为特征、复杂事件策略规则、联邦学习和对抗性机器学习治理等技术，旨在为发布/订阅、物联网遥测等分布式事件系统提供多层次、自适应的安全监控。
第一作者: Yuchen Zhang · 方向: AI 安全
工业控制系统异常检测大语言模型图学习时空依赖
Abstract:Industrial Internet systems face increasing threats from sophisticated industrial control system (ICS) attacks, resulting in critical safety incidents. However, existing tools exhibit limited effectiveness in real-time anomaly detection due to the complex dependencies among sensors and actuators. To tackle this, we present IstGPT, the first industrial anomaly detection tool based on LLMs and graph learning to provide real-time protection against a wide range of ICS attacks. IstGPT achieves fine-grained and precise modeling on spatial-temporal dependencies in industrial cyber-physical systems. It first leverages industrial multi-modal knowledge, including operational data, technical documents, and system diagrams, to extract sensor-actuator dependency graphs via multi-stage prompt engineering. Then, LLM-Optimation iteratively refines the graph based on node accuracy, edge...
论文介绍 工业物联网系统面临复杂ICS攻击威胁，现有工具因传感器与执行器间的复杂依赖而实时检测效果有限。本文提出IstGPT，首个结合LLM与图学习的工业异常检测工具。它利用工业多模态知识（如运行数据、技术文档）通过多阶段提示工程提取传感器-执行器依赖图，进而建模工业信息物理系统中的细粒度时空依赖关系，旨在实时检测广泛的ICS攻击。
第一作者: Mengnan Zhao · 方向: 隐私保护
扩散模型概念遗忘隐私保护组件解耦模型编辑
Abstract:Text guided diffusion models have revolutionized image synthesis but also raise ethical concerns, such as privacy violation and harmful content generation. To mitigate these issues, prevailing methods typically leverage an alignment mechanism, with predefined erasure references, to fine-tune pretrained model weights. However, these techniques are intrinsically limited by the representational capacity of textual space and display high sensitivity to the choice of predefined erasure references, e.g., suboptimal references may significantly affect the model utility preservation during erasure. To overcome these limitations, we introduce CoreUnlearn, aiming to disentangle and remove the erasure-critical component of the undesirable concept. Specifically, CoreUnlearn comprises a Component Extraction Module (CEM) and a Swap Disentangling Strategy (SDS). Guided by SDS, CEM is...
论文介绍 文本引导扩散模型的普及引发了隐私和伦理问题，现有概念遗忘方法依赖预定义的擦除参考文本，受文本空间表示能力限制且敏感。本文提出CoreUnlearn，旨在解耦并移除待遗忘概念的关键组件。该方法包含一个组件提取模块和交换解耦策略，通过学习和擦除概念的关键组件而非依赖文本参考，以更精准地控制遗忘过程，同时更好地保留模型的整体效用。
第一作者: Yoshinari Fujinuma · 方向: AI 安全
LLM代理技能注入攻击防御机制安全评估访问控制
Abstract:Large language model (LLM) agents increasingly rely on reusable skills i.e. documents describing task-specific procedures. However, this introduces a new attack surface for agents to manage. We study two complementary directions for this threat. First, we evaluate guardian-based defenses: an intermediary LLM agent that acts as a mediator for skill file access (dynamic guardian) or pre-rewrites these files at build time (static guardian). Across three LLM agent families, our guardians cut attack success rate (ASR) by well over half while preserving task utility. Second, we stress test them through attack reframing using four attacks that preserve the malicious instruction but change the phrasing. For non-guardian setup, the reframing pushes the ASR up to 81.4\%, but the dynamic guardian brings it down to 18.6\%, showing that real-time mediation is a robust defense.
论文介绍 LLM代理依赖可重用的技能文档，这引入了新的技能注入攻击面。本文研究两种防御方向：评估基于守护者的防御（动态守护者实时调解、静态守护者预处理技能文件）以及通过重新措辞的攻击重构来压力测试它们。实验表明，动态守护者能将攻击成功率显著降低，同时保持任务效用，证明实时调解是一种鲁棒的防御策略。
第一作者: Ankur Sharma · 方向: 系统安全
智能体操作系统系统架构AI智能体操作系统控制平面
Abstract:Traditional operating systems were designed around deterministic programs, explicit control flow, and human initiated workflows. Their core abstractions processes, threads, system calls, files, and permissions assume bounded behavior and predictable interaction patterns. Agentic AI systems introduce a different execution model: long-lived, goal-directed entities that reason probabilistically, invoke tools dynamically, and adapt behavior based on feedback. While agents can be implemented as user-space applications today, their execution characteristics stress OS boundaries in scheduling, memory and state management, security, observability, and governance. This paper introduces the concept of an Agent Operating System (AOS), a systems architecture that integrates an agentic control plane into existing operating systems or, in some models, subsumes selected OS responsibilities...
论文介绍 传统操作系统基于确定性程序和人类发起的工作流设计，其核心抽象难以适应AI智能体的长生命周期、目标导向、概率推理等执行特性。本文提出「智能体操作系统」的概念，旨在将智能体控制平面集成到现有操作系统中，或在特定模型下接管部分操作系统职责。该架构旨在解决智能体系统在调度、状态管理、安全和可观测性等方面对操作系统边界带来的新挑战。
第一作者: Vincent Koc · 方向: 软件安全
代理技能安全扫描器分歧VirusTotal静态启发式分析SkillSpector
Abstract:Agent skills extend AI agents with reusable instructions, tools, scripts, references, and workflows, establishing a security boundary distinct from both model safety and traditional package-malware detection. ClawHub Security Signals is a sanitized dataset of 67,453 latest public OpenClaw skill versions. Each row pairs redacted this http URL content and sanitized bundled files where present with a final ClawScan registry verdict and evidence from three scanner families: VirusTotal, static heuristic analysis, and NVIDIA SkillSpector. Rather than estimating malicious-skill prevalence, we study scanner disagreement. The three scanners rarely flag the same skills: any pair overlaps on at most 10.4% of their combined positives, only 0.69% of skills are flagged by all three, and 81.9% of flagged skills are identified by a single scanner. The disagreement is structured by attack...
论文介绍 本文研究 AI 代理技能的安全边界，提出 ClawHub 安全信号数据集，包含 67,453 个技能版本。通过分析 VirusTotal、静态启发式分析和 NVIDIA SkillSpector 三个扫描器的检测结果，发现它们极少标记相同技能，分歧结构与攻击类型相关。这为理解扫描器局限性和改进恶意技能检测提供了见解。
第一作者: Darren Fürst · 方向: 网络安全
网络入侵检测无监督学习基础模型变分自编码器NetVAD
Abstract:Detecting zero-day exploits in production networks requires robust Intrusion Detection Systems (IDS). However, current unsupervised models struggle to match the performance of supervised classifiers, which are trained for specific attacks only. To bridge this gap, we leverage the emerging capabilities of Network Foundation Models. We propose \textit{NetVAD}, a strictly identifier-free Variational Autoencoder that projects representations from a frozen Foundation Model into a task-specific latent space, trained solely on benign traffic. Evaluated on ToN-IoT and IoT-23, NetVAD achieves highly competitive unsupervised performance. On ToN-IoT, it achieves a 98% Micro F1-score and a 96% Macro F1-score at an operational false positive rate. Unlike prior work, we show the model's performance transparently for all attack-classes of the datasets. While the architecture excels at...
论文介绍 本文提出 NetVAD，一种无标识符的变分自编码器，用于无监督网络入侵检测。利用网络基础模型的表征，将良性流量投影到任务特定潜在空间。在 ToN-IoT 和 IoT-23 数据集上评估，实现高竞争力的无监督性能，F1 分数达 98%。该方法为零日漏洞检测提供了新思路。
第一作者: Raj Patel · 方向: AI 安全
脉冲神经网络网络入侵检测神经元模型脉冲编码方案边缘部署
Abstract:Network intrusion detection is a core component of modern cybersecurity infrastructure, yet the deep learning models that dominate the field are computationally demanding, motivating interest in lightweight alternatives suited to edge and neuromorphic deployment. Spiking Neural Networks (SNNs) are therefore a natural candidate, but their design space, spanning the choice of neuron model and spike encoding scheme, remains poorly characterized for intrusion detection. We bridge this gap by using a controlled ablation study using 9 neurons coupled with 3 spike encoding schemes, making 27 variants, all implemented on snntorch evaluated over raw inputs with limited preprocessing on four benchmark datasets (NSL KDD, KDDCup99, CIC-IDS2017, and CTU-13) with 5 seeds. We find that spike encoding scheme is a better determinant for detection quality than the neuron model, where rate and...
论文介绍 本文评估脉冲神经网络（SNNs）配置用于网络入侵检测，探索神经元模型和脉冲编码方案的设计空间。通过受控消融研究，测试 27 种变体在四个数据集上的性能。发现脉冲编码方案比神经元模型更能影响检测质量，为轻量级入侵检测系统在边缘和神经形态部署提供参考。
第一作者: Abdelrahman Abouelenein · 方向: AI 安全
差分隐私数据存储生成检索增强推理局部敏感哈希隐私保护
Abstract:It is crucial for modern on-device AI systems that rely on retrieval-augmented inference to release and share datastores without compromising individual privacy. This can be achieved using Differential Privacy (DP), which provides a formal guarantee that ensures individual contributions remain indistinguishable, even under adversarial analysis. In this paper, we introduce a hashing-based probability generation framework designed to enable the creation and release of differentially private datastores. Our approach employs locality-sensitive hashing (LSH) to efficiently partition high-dimensional data into buckets. We then add calibrated DP noise to the accumulated vote for each bucket, generating a probability distribution across classes. Our method is broadly applicable to any pipeline requiring secure key,value datastore creation and release. We conducted experiments on seven...
论文介绍 本文引入基于哈希的概率生成框架，用于创建和发布差分隐私数据存储。采用局部敏感哈希（LSH）分割高维数据，并添加校准的差分隐私噪声生成类别概率分布。该方法适用于需要安全键值数据存储的任何管道，实验在多个数据集上验证了其有效性。
第一作者: Hansika Weerasena · 方向: 密码学协议
形式化验证安全加密虚拟化AMD SEV可信执行环境机密计算
Abstract:Trusted execution environments (TEEs) provide a secure environment for data and code in use, ensuring that they are protected with respect to confidentiality and integrity. Virtual machine (VM)-based TEEs utilize virtualization technology to create isolated execution spaces that can support a complete operating system or specific applications. AMD secure encrypted virtualization (SEV) is a key technology used in confidential computing in the cloud enabling hardware-based memory encryption to protect sensitive data within VMs. However, AMD SEV often operate without formal assurances of their security guarantees. Our research introduces a formal framework for representing and verifying AMD SEV confidential VMs. Specifically, we conduct design-level and property-level abstraction on AMD SEV specification and conduct property checking on the model to ensure confidentiality...
论文介绍 本文提出一个形式化框架，用于表示和验证 AMD 安全加密虚拟化（SEV）机密虚拟机。通过设计级和属性级抽象，对 SEV 规范进行建模，并执行属性检查以确保机密性和完整性。这为云计算中的机密计算提供了形式化安全保证。
第一作者: Michael J. Bommarito II · 方向: 软件安全
漏洞研究目标选择LLM 辅助Windows 二进制符号恢复
Abstract:The attack surface of a modern operating system is a haystack: thousands of signed binaries and millions of functions, almost none relevant to any given vulnerability. A human analyst or an LLM agent must pick the function worth reading before analyzing it. At whole-OS scope, this target selection, not the analysis, is the binding constraint. We present Symbolicate-Enrich-Sample, a low-cost batch pipeline that turns a corpus of production Windows binaries into a queryable, priority-ranked research queue. We (i) recover function-level symbols for stripped vendor binaries by auto-fetching the public symbol files and joining them to a recovered call graph; (ii) attach cheap, deterministic structural features to each named function and, conditioned on those features, use a low-cost language model to assign a reachability tier, a risk level, a bug-class hypothesis, and a rationale...
论文介绍 本文提出 Symbolicate-Enrich-Sample 管道，用于大规模 Windows 漏洞研究中的目标选择。通过自动获取公共符号文件，恢复函数级符号，并附加结构特征，使用语言模型分配可达性层级和风险级别。该方法将函数集转化为优先级排序的研究队列，提高了漏洞分析效率。
第一作者: Hasan Coşkun · 方向: 隐私保护
隐私保护智能监控暴力检测秘密共享证据治理
Abstract:AI-enabled surveillance can accelerate public-safety response, yet most systems still leave recorded evidence under centralized administrative control. This paper proposes a privacy-preserving smart surveillance framework that separates incident detection from evidence disclosure. A lightweight MobileNetV2-based video classifier detects violent clips, while each recorded incident segment is immediately encrypted and made accessible only through threshold-based approval. The decryption key is split with Shamir's Secret Sharing, member shares are protected with public-key cryptography, and voting is supported by time-limited tokens, two-factor authentication, signatures, and audit logs. This study evaluates MobileNetV2+LSTM, MobileNetV2+BiLSTM, and MobileNetV2+temporal CNN heads on SCVD, RWF-2000, and Real-Life Violence Situations under seven in-domain and cross-dataset...
论文介绍 本文提出隐私保护智能监控框架，分离事件检测和证据披露。使用 MobileNetV2 进行暴力检测，检测到的事件段加密存储，通过基于阈值的批准访问。采用 Shamir 秘密共享分割解密密钥，结合公钥密码学和审计日志，实现去中心化证据治理。实验评估了多种模型在跨数据集上的性能。
第一作者: Tiziana Liberati · 方向: 密码学协议
后量子密码学学习与错误密钥封装机制GPU 加速OpenACC
Abstract:Shor's algorithm proved that asymmetric cryptographic protocols based on the integer factorization and discrete logarithm problems are no longer safe in a world with large-scale quantum computers. As a result, Post-Quantum Cryptography (PQC) has been developed over the last few years, seeking cryptographic primitives resistant to quantum attacks. One of the main hard problems underlying PQC schemes is the Learning with Errors (LWE) problem, which is significantly more computationally intensive than its classical predecessors. In this work, we present a Key Encapsulation Mechanism (KEM) based on plain LWE and develop a GPU-oriented implementation using OpenACC. We evaluate the performance of our accelerated application in terms of both time-to-solution and energy-to-solution, considering bare-metal and containerized executions across multiple NVIDIA GPU models and generations...
论文介绍 本文展示基于学习与错误（LWE）的密钥封装机制（KEM）的 GPU 加速实现，使用 OpenACC 编程模型。评估在多个 NVIDIA GPU 模型上的性能，包括时间和能耗。该工作为后量子密码学的高效实现提供了 GPU 加速方案，支持云计算环境。
第一作者: Seonwoo Kim · 方向: AI 安全
威胁情报知识图谱构建本体发现模式无关网络安全
Abstract:Cyber threat intelligence (CTI) reports now serve as essential resources for capturing adversary tactics, techniques, and procedures observed in modern attack campaigns. While traditional CTI platforms reduce this intelligence to isolated indicators through fixed schemas such as STIX, ontology-based representations preserve the semantic relationships needed for structured threat analysis. However, existing approaches for ontology-aligned CTI extraction face three challenges: (i) schema-specific pipelines that require manual reconfiguration whenever the schema changes, (ii) prompt-based schema inclusion that fails to scale on large ontologies such as UCO, and (iii) reliance on enterprise LLM APIs that conflicts with privacy constraints when integrating sensitive internal incident data. In this paper, we present ANCHOR, a schema-agnostic CTI knowledge graph construction system...
论文介绍 现有网络安全威胁情报知识图谱构建方法存在对特定模式依赖、难以扩展和隐私顾虑等挑战。本文提出系统ANCHOR，采用混合本体发现方法，构建与具体模式无关的威胁情报知识图谱。该方法旨在解决传统方法需要手动配置、在大型本体上扩展性差以及依赖外部API带来的隐私问题。
第一作者: Yunhao Feng · 方向: 安全研究
智能体安全开放世界威胁自进化防御安全训练计算机使用智能体
Abstract:Computer-use agents extend language models from text generation to sustained interaction with files, terminals, browsers, and external tools. This shift creates safety risks that are difficult to detect from isolated prompts or final responses, because harm often emerges only through multi-step execution traces whose individual actions appear locally benign. We introduce BraveGuard, a self-evolving defense framework for training guard models from open-world threat signals and realistic agent trajectories. BraveGuard mines recent research sources to identify emerging risks and attack patterns, instantiates them as executable computer-use tasks, collects agent rollouts, and derives trajectory-level supervision for guard model training. As new threats and validation failures appear, the pipeline can be repeated, yielding an adaptive defense loop rather than a static...
论文介绍 计算机使用智能体与外部环境交互，其安全风险常源于多步骤执行轨迹中单个动作的局部良性。本文提出BraveGuard自进化防御框架，通过挖掘公开威胁信号和实际智能体轨迹来训练防护模型。该框架可收集新兴攻击模式并生成轨迹级监督数据，形成动态防御闭环以应对不断变化的威胁。
第一作者: Thamilvendhan Munirathinam · 方向: 安全研究
智能体记忆内存管理标准化治理JSON-Schema
Abstract:Agent-memory frameworks - mem0, Letta/MemGPT, Cognee, Zep/Graphiti, MemoryOS, MemTensor - each ship their own SDK, storage layout, and operational vocabulary. There is no shared wire format: every integration is bespoke, every migration rebuilds memory from scratch, and no framework ships a governance surface that lets a human review writes before they enter long-term storage. We present memorywire, a JSON-Schema 2020-12 wire format for five memory operations (remember, recall, forget, merge, expire) over four memory types (semantic, episodic, procedural, emotional), with a MemoryStore interface, a fan-out router, and an optional HITL governance channel. We describe an open-source reference implementation with five backend adapters (sqlite-vec, mem0, Letta, Cognee, pgvector); a microbenchmark on a 100-fact / 50-query labelled corpus achieving recall@5 = 1.000 on the 42...
论文介绍 当前各类智能体记忆框架采用各自专有的接口和存储格式，导致集成迁移困难且缺乏统一的治理机制。本文提出memorywire，一个基于JSON-Schema的通用线格式，定义了记忆操作接口和类型规范。该工作旨在通过标准化格式实现不同记忆后端的互操作性，并为人工审核提供治理通道。
第一作者: Hassan Touheed · 方向: 密码学协议
零知识证明隐私保护多智能体协作语义路由密码学协议
Abstract:Foundational agent interoperability standards, notably the Agent-to-Agent (A2A) protocol and the Model Context Protocol (MCP), have advanced multi-agent system communication, and complementary identity frameworks leveraging W3C Decentralised Identifiers (DIDs) and Verifiable Credentials (VCs) provide cryptographic agent authentication. However, no existing protocol supports content-based semantic routing of agent payloads across organisational trust boundaries without requiring the routing intermediary to decrypt the payload, which is a hard constraint in compliance-sensitive environments governed by GDPR, HIPAA, and MiFID II. We propose SS-ZKR, a three-mechanism privacy-preserving routing protocol designed as a complementary layer atop A2A/MCP. Mechanism I introduces blind routing via differentially private semantic intent vectors cryptographically bound to zero-knowledge...
论文介绍 在多智能体协作中，跨组织信任边界的内容路由要求保护负载隐私，现有协议无法在路由中继不解密负载的前提下进行语义路由。本文提出SS-ZKR协议，作为A2A/MCP协议的补充层，通过零知识证明和差分隐私技术实现隐私保护的语义路由，以满足GDPR等合规要求。
第一作者: Ismail Hossain · 方向: 安全研究
智能体技能供应链安全安全基准测试恶意行为检测开放生态
Abstract:Open agent platforms allow community contributors to publish reusable skills that agents can invoke at runtime. This extensibility also creates a supply-chain risk: malicious contributors can hide harmful behavior inside skills that appear benign under superficial inspection. However, existing defenses are hard to evaluate because there is no benchmark that measures both malicious-skill detection and runtime verification. We present SkillVetBench, a two-stage security vetting benchmark for open agentic skill ecosystems. The first stage performs semantic vetting over each skill's natural-language specification to detect hidden malicious intent. The second stage executes flagged skills in an instrumented sandbox to observe runtime behavior and collect auditable evidence. We build a benchmark from confirmed malicious skills in the live OpenClaw ecosystem, including samples from...
论文介绍 开放智能体平台允许社区发布可复用技能，这带来了恶意技能隐藏有害行为的供应链风险。然而，目前缺乏同时评估恶意技能检测与运行时验证的基准。本文提出SkillVetBench基准测试，通过语义审查和沙箱执行两阶段方法，对开放技能生态系统的安全风险进行检测和验证。
第一作者: Ehood Porat · 方向: 系统安全
协议安全旁路攻击伪随机数生成器IPv6系统安全
Abstract:We present a novel, practical attack on the IPv6 Fragment ID generation algorithm of XNU, which is the kernel used by Apple products such as macOS and iOS. This attack exploits a race-condition vulnerability in the algorithm's pseudorandom number generator (PRNG) to cryptanalytically break, learn the internal state of the generator, and consequently predict fragment IDs, which, in turn, facilitates an IPv6 fragment spoofing attack. As far as we know, this is the first cryptanalytic attack that is based on exploiting race-conditions. With fragment spoofing, it is possible to partially manipulate UDP datagrams and TCP segments. We showcase a new type of attack on NFS (UDP) where an off-path attacker modifies a file as it is written, and an attack on HTTP (TCP) where an off-path attacker modifies an HTTP request. Apple assigned this vulnerability the CVE identifier CVE-2024-27823...
论文介绍 本文揭示了苹果XNU内核中IPv6分片ID生成算法的一个竞争条件漏洞。攻击者可利用该漏洞，通过竞争条件对伪随机数生成器进行密码分析，从而预测分片ID并实施分片欺骗攻击。此攻击可被用于篡改UDP和TCP数据，对NFS和HTTP等协议构成实际威胁。
第一作者: Yingao Elaine Yao · 方向: 安全研究
无人机安全蜂群控制GPS欺骗模糊测试漏洞发现
Abstract:Swarm robotics, particularly drone swarms, are used in various safety-critical tasks. While a lot of attention has been given to improving swarm control algorithms for improved intelligence, the security implications of various design choices in swarm control algorithms have not been studied. We highlight how an attacker can exploit the vulnerabilities in swarm control algorithms to disrupt drone swarms. Specifically, we show that the attacker can target a swarm member (target drone) through GPS spoofing attacks, and indirectly cause other swarm members (victim drones) to veer from their course, resulting in collisions. We call these Swarm Propagation Vulnerabilities (SPVs). In this paper, we introduce two fuzzing tools, SwarmFuzzGraph and SwarmFuzzBinary, to efficiently find SPVs in swarm control algorithms. SwarmFuzzGraph uses a combination of graph theory and...
论文介绍 无人机蜂群的安全性设计尚未得到充分研究，其控制算法漏洞可被攻击者利用。本文表明，针对单个无人机的GPS欺骗攻击可能引发蜂群传播漏洞，导致其他无人机偏航甚至碰撞。为此，作者引入了两种模糊测试工具，用于高效发现蜂群控制算法中的此类传播性漏洞。
第一作者: Uche Unoke Emmanuel · 方向: 系统安全
钓鱼检测实时检测URL特征轻量级框架多层感知机
Abstract:Phishing attacks remain a major cybersecurity threat, exploiting deceptive URLs to steal sensitive user information. Traditional blacklist and rule-based detection approaches are reactive and often fail to identify newly emerging phishing URLs. This paper proposes a lightweight hybrid framework for real-time phishing URL detection that combines blacklist-based screening with a Multi-Layer Perceptron (MLP) classifier operating solely on structural URL features. The framework extracts 16 URL-derived features capturing structural, domain-based, and security-related characteristics without requiring webpage content access, third-party APIs, or visual rendering, making it computationally efficient for real-time deployment. The system was trained and evaluated on the PhiUSIIL phishing dataset containing 235,795 labelled URLs. Experimental results show that the proposed MLP achieved...
论文介绍 传统钓鱼URL检测方法存在反应滞后和难以识别新URL的问题。本文提出一个轻量级混合框架，结合黑名单筛查和仅基于URL结构特征的多层感知机分类器。该方法无需访问网页内容，计算高效，适用于实时部署，旨在通过提取URL的结构、域和安全相关特征来提升检测能力。
第一作者: Alexandre Dulaunoy · 方向: 系统安全
漏洞识别去中心化模型CVE漏洞发布操作增强
Abstract:The Global CVE initiative (GCVE) proposes a decentralized, open, and extensible model for vulnerability identification, publication, and enrichment. It addresses a gap in today's vulnerability ecosystem: centralized systems provide rigorous control and widely recognized identifiers, while many producers publish advisories independently without a shared fabric for discovery, correlation, enrichment, and reuse. This paper presents GCVE as a socio-technical standardization effort combining autonomous GCVE Numbering Authorities, lightweight allocation rules, distributed publication, open Best Current Practices, and practical reference implementations. The model preserves global uniqueness while allowing participants to publish according to their operational needs. It also broadens the concept of a vulnerability record to cover assignments, disclosures, sightings, rejected...
论文介绍 本文针对当前漏洞生态系统中集中控制与分散发布之间的差距，提出全球CVE倡议（GCVE）模型。该模型结合自主编号机构、轻量级分配规则和分布式发布机制，实现漏洞信息的去中心化识别、发布和增强，支持发现、关联与重用，旨在提升漏洞管理的灵活性和广泛覆盖。
第一作者: Subhadip Mitra · 方向: AI 安全
对抗攻击跨代转移安全对齐LLMs质量多样性进化
Abstract:Safety alignment in LLMs does not improve monotonically across model generations. Studying four generations of Google's Gemma family (7B-31B) with quality-diversity evolution (MAP-Elites) as an automated red-teaming probe, we find that Gemma 3 (12B) exhibits 68.7% +/- 5.7% attack success rate (ASR; mean +/- std, 3 seeds), significantly higher than its predecessor Gemma 2 (45.5% +/- 7.2%; p = 0.030, paired bootstrap) and its successor Gemma 4 (33.9% +/- 1.8%). Replaying evolved attack archives across generations reveals that attacks from other generations transfer to Gemma 3 at 44-46% but only 14-18% to Gemma 4, indicating that Gemma 4's safety gains generalize beyond the attack distributions evolved against earlier generations. Under our 8B judge, copyright and cybercrime vulnerabilities register at near-100% across all generations, though a second-judge audit (Section 6)...
论文介绍 研究大型语言模型（LLMs）安全对齐在模型代际间的非单调性。通过质量多样性进化（MAP-Elites）自动化红队测试，分析攻击在Gemma家族四代模型间的转移率，发现安全对齐并非持续改进，且攻击转移模式揭示了不同代模型的漏洞特征，为安全评估提供新视角。
第一作者: Subhadip Mitra · 方向: AI 安全
质量多样性进化LLM安全漏洞发现对抗测试MAP-Elites
Abstract:Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode collapse, and gradient-based approaches produce uninterpretable gibberish. We introduce a quality-diversity evolutionary framework that operates at the semantic level, evolving interpretable attack strategies rather than token sequences. Using MAP-Elites, we maintain a diverse archive of attacks across behavioral dimensions (strategy type, encoding method, prompt length). In experiments across GPT-4o-mini, Claude 3.5 Sonnet, Gemini 2.0 Flash, and an open-weight coding model (Devstral-small-2), we discover distinct vulnerability profiles: GPT-4o-mini is vulnerable to hypothetical and multi-turn framing combined with ROT13 encoding (fitness 0.8), Gemini to direct attacks with ROT13 and multi-turn with Leetspeak (0.8), while Claude shows...
论文介绍 针对现有LLM对抗测试方法覆盖不足的问题，本文引入质量多样性进化框架，在语义层面进化可解释的攻击策略。使用MAP-Elites维护多样攻击存档，跨多个模型实验发现不同漏洞配置文件，以更全面地揭示LLM安全弱点，弥补手动红队和模式崩溃方法的局限。
第一作者: Sanjay Rawat · 方向: 软件安全
神经符号系统漏洞发现LLMDatalogSMT
Abstract:Vulnerability discovery on C/C++ source asks the analyst to choose between heavyweight static analysers, which need a working build before a single query runs, and free-form LLMs, which read source readily but invent details and lose track of cross-function dataflow on real codebases. We present NeuroLog, an end-to-end build-free pipeline that assigns each layer the role it is uniquely good at: an LLM extracts typed dataflow facts one function at a time; a Souffle rule mesh composes those facts into cross-function findings; a Z3 post-pass filters infeasible findings and emits a SAT model for each survivor. To go beyond pure static reasoning we also fold in runtime evidence: likely range invariants from a handful of corpus seeds tighten the SMT problem at near-zero cost. A second LLM agent reads each SAT model and writes a Python program that produces a candidate crashing...
论文介绍 解决C/C++源码漏洞发现中静态分析器和LLMs的权衡难题。提出NeuroLog管道，结合LLM提取类型数据流事实、Datalog规则进行跨函数推理、Z3过滤不可行发现，并整合运行时证据。该混合方法提供可审计的漏洞发现流程，提升准确性和可解释性。
第一作者: He Wang · 方向: 安全研究
后门攻击主动可用后门社会工程LLM安全对话诱导
Abstract:Current backdoor attacks against LLMs are typically manipulated by the attacker and remain passive. In this paper, we introduce the \textbf{Proactive Availability Backdoor (PAB)}, a novel paradigm that shifts the attack vector from passive waiting to active social engineering. By weaponizing the inherent helpfulness of aligned LLMs, PAB proactively traps users into executing trigger-implanted queries by offering suggestions, achieving high aggressiveness, precision and stealthiness. To rigorously evaluate its threat in a real-life context, we introduce a dual-agent ecological simulation framework based on selected dimensions of the Five-Factor Model, and deploy PAB with few-shot prompts. Being validated on different models and domains, PAB performs remarkably and its effective attack success rate, which calculates the joint probability of attack incidence rate and attack...
论文介绍 针对LLM后门攻击的被动性限制，本文提出主动可用后门（PAB）范式。PAB通过对话诱导利用LLMs的有用性，主动诱使用户执行触发查询。引入双代理生态模拟框架评估其威胁，实验显示攻击在多个模型上具有高成功率，揭示了新型社会工程攻击向量。
第一作者: Minh-Luân Nguyen · 方向: 软件安全
漏洞复现声明式框架NixOSCVE机器可检查
Abstract:Reproducing software vulnerabilities is fundamental to security researchers, open-source maintainers, and educators. Yet, vulnerabilities remain hard to reproduce today, and even when they can be reproduced, recreating a software environment where the vulnerability can be exploited becomes harder and harder over time. We present NICE, the NIx CvE reproduction framework, which uses declarative recipes to build and automatically validate vulnerable environments. In NICE, a reproduced CVE comprises one or more NixOS virtual machine configurations, a scripted exploitation scenario, and machine-checkable assertions that provide factual evidence of exploitation. This design facilitates sharing, validation, review, and long-term reproducibility. We evaluate NICE on 19 diverse real-world CVEs spanning multiple CWE categories, attack vectors, and target types (user-space, system...
论文介绍 软件漏洞复现面临环境构建和维护困难。本文提出NICE框架，使用声明式配方（如NixOS配置）自动构建漏洞环境，结合脚本化利用场景和机器可检查断言。该设计促进CVE的长期复现、验证和分享，支持安全研究与教育应用。
第一作者: Shubhashis Sengupta · 方向: AI 安全
真实性债务合成内容信任框架出处AI治理
Abstract:Generative artificial intelligence has fundamentally changed how content is now produced. It has enabled how high-fidelity text, images, audio, and videos are created, modified, and redistributed at near-zero marginal cost. This shift exposes enterprises and ecosystems to a number of risks across four reinforcing authenticity layers -- authenticity, provenance, integrity, and accountability -- that traditional controls are inadequate to address in isolation. We introduce the concept of authenticity debt: the cumulative institutional liability that accumulates when organizations deploy AI-generated content without preserving verifiable origin, integrity, and accountability, deferring exposure that surfaces under regulatory, legal, or market scrutiny. This paper presents a comprehensive, multi-dimensional taxonomy of generative AI harms and attack vectors, surveys the...
论文介绍 生成AI导致高保真内容泛滥，引入真实性债务概念描述组织未保留可验证出处时的累积负债。论文提出多层框架，涵盖真实性、出处、完整性和问责维度，系统分类AI生成内容的危害与攻击向量，旨在指导风险管理和合规治理。
第一作者: Soham Roy · 方向: 网络安全
PII泄露自主网络代理社会工程攻击基准测试网络安全
Abstract:Deceptive web content, widely instantiated across the internet and commonly known as \textit{social-engineering attacks}, manipulates autonomous web agents into submitting users' personally identifiable information (PII) to attacker-controlled endpoints. In this paper, we show that social-engineering attacks are highly effective at extracting critical-tier PII from frontier web agents, posing a severe risk to deployed agentic systems. To quantify this risk, we introduce \textbf{\textsc{Scammer4U}}, a pre-registered benchmark of 91 attacker-controlled environments and 10 benign-twin baselines, spanning 8 attack vectors and 16 site categories on an 8-axis factorial taxonomy that isolates the causal contribution of individual attack design factors. Across frontier agents, we find that critical-tier PII leakage reaches 54--93\% under no privacy guidance, compared to 0\% on...
论文介绍 自主网络代理易受欺骗性内容攻击，导致用户个人可识别信息（PII）泄露。本文提出Scammer4U基准，包含91个攻击环境和10个基线，评估8种攻击向量。实验显示关键PII泄露率达54-93%，凸显代理安全设计的紧迫性，为防御研究提供量化基础。
第一作者: Chao Wang · 方向: AI 安全
跨应用上下文中毒间接提示注入第一方APIChatGPT AppsAI安全
Abstract:ChatGPT Apps, launched by OpenAI on Oct. 6, 2025, introduce an app-in-app paradigm in which third-party applications share a single chat context with the user and with every other connected app. The ecosystem grew from 122 apps in Dec. 2025 to 888 by May 2026, yet its security has remained uninvestigated. We identify cross-app context poisoning, a variant of indirect prompt injection distinguished by three properties: 1) the injection persists in the shared chat context across turns; 2) the effect surfaces through a different co-resident app the user later invokes; and 3) the delivery vectors are first-party APIs exposed to every connected app. We find multiple APIs capable of writing app-controlled content into the shared context, with sendFollowUpMessage as the most direct and potent channel. Two undocumented parameters that the runtime silently accepts, systemPrompt and...
论文介绍 研究ChatGPT Apps生态系统中第三方应用共享聊天上下文引发的安全问题。核心方法识别了一种跨应用上下文中毒攻击，该攻击通过第一方API（如sendFollowUpMessage）向共享上下文注入持久内容，影响其他应用行为。这揭示了新范式下的安全风险，为API设计和AI安全治理提供参考。
第一作者: Song-Kyoo Kim · 方向: 安全研究
网络安全随机分析防御策略单攻击场景指数分布
Abstract:This research presents a novel stochastic framework for proactive cybersecurity defense timing under a single attack scenario. The approach models the defense process as a continuous observation mechanism in which the defense instant and the subsequent observation slot follow independent exponential distributions. Laplace-Carson transforms combined with first-excess theory yield the joint detection function that brackets the attack moment. Marginalization under Markovian Poisson arrivals then produces the probability density of the defense moment and conditional expectations of pre-attack and post-attack observation times. These closed-form results enable quantitative assessment of defense timing sensitivity to threat intensity and support precise calibration of observation parameters for low-latency proactive measures. Major contributions include the explicit derivation of...
论文介绍 提出一个随机框架，用于分析单攻击场景下的网络安全防御时机。将防御过程建模为连续观察机制，使用指数分布和Laplace-Carson变换推导检测函数，得出防御时刻概率密度。该工作支持对威胁强度敏感性进行量化评估，有助于校准低延迟主动防御参数。
第一作者: Yunseong Kim · 方向: 软件安全
内核模糊测试数据流提取LLVMKCOV边缘覆盖
Abstract:Coverage-guided kernel fuzzers such as syzkaller rely on edge coverage (trace-pc) as their sole feedback signal. This context-blind approach cannot distinguish execution paths that differ only in argument values. for example, two invocations of copy_from_user() with different size parameters hit identical basic blocks yet have vastly different security implications. We present BOUNDARY FLOW, an LLVM-based instrumentation framework that extends Linux KCOV with data-flow extraction of function arguments and return values. A compiler pass (-fsanitize-coverage=dataflow-args, dataflow-ret) emits lightweight callbacks capturing a structured tuple <PC, arg_idx, arg_size, ptr, offsets[]> at function entry and <PC, ret_size, ptr, offsets[]> at return. Composite types are automatically decomposed via DWARF DICompositeType metadata with zero source annotation. A separate kernel...
论文介绍 针对内核模糊器依赖边缘覆盖、无法区分不同参数值执行路径的问题，提出BOUNDARY FLOW框架。基于LLVM插桩，在函数边界提取参数和返回值的数据流，扩展Linux KCOV。该方法自动分解复合类型，无需源码注解，提升了内核安全测试的精确性。
第一作者: Naci Cankaya · 方向: 软件安全
AI推理验证位精确GPU浮点确定性计算AI治理
Abstract:Verifying claims about AI workloads is a pre- requisite for credible AI governance of covert adversaries (who comply with monitoring only when detection likelihood is high), yet the ap- parent non-determinism of GPU floating-point arithmetic forces auditors to accept approximate output matches. Covert adversaries can exploit un- verifiable degrees of freedom in monitored compu- tation. Attack vectors include steganography, un- reported modification of inference software, and covert computation via unreported batch elements. Empirically, we analyze how modern inference engines (vLLM, HF transformers) produce deter- ministic but non-invariant outputs, without need- ing to set performance-compromising determin- ism flags, if the right information is available for re-computation and no atomic functions are called in the backend. We demonstrate that such bitwise- precise...
论文介绍 解决AI推理中GPU浮点算术非确定性导致验证困难的问题。核心方法在不设置性能妥协标志的情况下，实现位精确的推理输出验证，避免隐蔽对抗者利用未报告的修改或批处理元素。这为可信AI治理提供了可审计基础，适用于隐蔽对抗场景。
第一作者: Naoki Kitamura · 方向: 密码学协议
社交推理游戏狼人游戏无主持人协议密码学协议扑克牌
Abstract:Social deduction games, or hidden-role games, are multiplayer games in which players are assigned private roles and act under asymmetric information about other players' roles and actions. In the canonical example Werewolf, werewolves conceal their roles and mislead the other players, while the seer can obtain role information about a chosen player. Thus, a central functionality of such games is controlling which players can access which information. In typical play, this control is implemented by a trusted human moderator, who assigns roles, mediates secret actions, and reveals outcomes. This reliance raises the barrier to participation and introduces a trusted third party as a single point of failure. In this work, we show that Werewolf can be played without a moderator or any digital device, using only ordinary playing cards. Our construction maintains a shared pool of...
论文介绍 针对狼人游戏等社交推理游戏依赖可信主持人的问题，提出一种无主持人协议。仅使用普通扑克牌实现角色分配、秘密行动和结果揭示，无需数字设备。该协议降低了参与门槛，消除了第三方单点故障，展示了密码学在游戏设计中的应用。
第一作者: Rebecca Balebako · 方向: 软件安全
代码安全比较LLM生成代码静态分析动态分析自动化框架
Abstract:Large language models (LLMs) are rapidly transforming how software is created and maintained. Comparing LLM-generated code against human-written standards is essential to determine whether these new tools uphold or erode the security baselines established by professional developers. Yet, we lack a standardized method for empirically comparing the security of code produced through human-LLM collaboration against LLM-only, or traditional human-only methods. To facilitate this, we propose an automated framework for conducting comparative studies across human-only, LLM-only, and hybrid conditions. Our approach automates the logging of prompts, timing, and experimental settings, measuring outcomes through multi-dimensional static and dynamic quality analysis. We provide an open-source implementation of this framework to ensure that future researchers can conduct reproducible...
论文介绍 提出一个自动化框架，用于比较人类编写代码、LLM生成代码和混合方法的安全性。通过记录提示、时间和实验设置，使用多维度静态和动态质量分析测量结果。该框架开源，旨在标准化评估过程，确保LLM工具不侵蚀专业开发者建立的安全基线。
第一作者: Nadav Schweitzer · 方向: 网络安全
移动自组网路由层防御OLSR协议行为推断网络安全
Abstract:Mobile ad hoc networks (MANETs) based on proactive routing protocols such as OLSR remain vulnerable to routing-layer attacks. While prior work has focused primarily on attack detection, the problem of identifying deployed defenses has received comparatively little attention. This work examines whether the presence of a routing-layer defense can be inferred from features derived exclusively from externally observable routing and control-plane behavior. The evaluated Fictive Mitigation mechanism operates entirely within standard OLSR control traffic and introduces no new packet types, making passive detection inherently difficult. Using ns-3 simulations across baseline, attack-only, defense-only, and combined attack-defense regimes under both static and mobile conditions, we derive features from observable routing dynamics and control-plane activity available to a passive...
论文介绍 研究在基于OLSR的移动自组网中，从外部可观察的路由和控制平面行为推断防御机制的存在。通过ns-3模拟，在静态和移动条件下提取特征，评估Fictive Mitigation机制。该工作探索被动检测防御的可行性，为网络攻击检测和防御识别提供新思路。
第一作者: Muhammad Khuram Shahzad · 方向: AI 安全
物联网入侵检测SMOTE过采样类不平衡侧信道数据多模型评估
Abstract:The detection of intrusions in IoT-based networks poses challenges that cannot be overcome using traditional machine learning methods. Perhaps the biggest of them is related to the presence of a class imbalance in the side-channel dataset, where the number of samples in the normal class compared to the attacks can reach a ratio of 75,964 to 1. Such an aspect is addressed by Dominguez et al. through the proof of concept of power-based intrusion detection. Unfortunately, neither the authors attempt to cope with the problem of imbalance nor do they assess the classifier performance using a balanced training set. In the current paper, both aspects will be handled at once. First, a Synthetic Minority Oversampling Technique (SMOTE) was performed on all nine possible datasets extracted from the initial one, providing an exact imbalance ratio of 1.1 for each. Then, eight algorithms...
论文介绍 针对物联网入侵检测中侧信道功率数据类不平衡严重的问题，应用SMOTE技术对九个数据集进行过采样，使不平衡比达到1.1。然后使用多种机器学习算法进行评估。该工作提高了入侵检测模型的性能，为处理类不平衡的IoT安全系统提供方法。
第一作者: Junbo Zhang · 方向: AI 安全
LLM安全数据过滤安全微调安全退化
Abstract:Large language models (LLMs) suffer from degraded safety capabilities even when fine-tuned with benign datasets. However, existing methods for identifying safety-degrading samples in benign datasets suffer from high computational costs and significant noise issues. In this paper, we propose DataShield to efficiently and effectively identify potential safety-degrading samples. Our key intuition is based on the observation that benign fine-tuning increases the overall response compliance of LLMs. DataShield's key technical insight is to quantify each sample's contribution to the model's compliance behavior as its safety degradation score. DataShield consists of three core components: (1) Compliance Vector Extraction, which captures the LLM's compliance behavior tendency; (2) a novel Compliance-Aware Score (CAS), which automatically identifies the optimal safety-critical layer...
论文介绍 该研究针对大型语言模型在良性数据集微调后安全能力下降的问题，提出一种名为DataShield的数据过滤框架。该方法通过量化数据样本对模型响应合规性的贡献，计算其安全退化分数，以高效识别潜在风险样本。其核心包括合规向量提取和合规感知评分技术，旨在改善模型安全性的同时降低计算成本。
第一作者: Vivek Kumar Sharma · 方向: 密码学协议
网络入侵检测协议语言模型加密流量分析元数据
Abstract:Modern network intrusion detection systems (NIDS) are caught in a structural contradiction: the protocols carrying the highest threat intelligence are precisely those encrypted under TLS 1.3 and QUIC, where payload inspection yields nothing. We ask a simpler question -- what if the attack signature is not in the bytes, but in the rhythm? -- and answer it by treating network flows as a language whose grammar is written entirely in L3/L4 packet metadata: length, inter-arrival time, TTL, TCP flags, and hashed port numbers. We present PLM-NIDS, which proves three claims in sequence. (1) The grammar exists and is learnable: a RWKV-4 state-space model trained on 344,232 unlabelled Monday flows achieves a causal LM validation loss of 0.204, demonstrating that benign traffic has predictable, statistically consistent structure. (2) Attacks violate this grammar: the per-flow perplexity...
论文介绍 针对加密流量下传统深度包检测失效的挑战，本文提出PLM-NIDS系统。该系统将网络流视为一种语言，仅利用IP/TCP层的元数据（如包长度、到达间隔时间）来学习正常流量的统计结构。实验表明，恶意流量会违背这种学到的「语法」，从而实现对加密网络入侵的检测，无需解密载荷。
第一作者: Mingxuan Zhang · 方向: AI 安全
LLM代理隐私泄露获取阶段审计基准测试
Abstract:LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users. However, agents often acquire more sensitive information than the task requires. Existing privacy benchmarks audit what the agent's response or outgoing actions disclose, but overlook the acquisition stage where data first enters the agent's context. The over-acquired information is then one careless action or one attack away from an outright leak. To assess its prevalence, we introduce \emph{PrivacyPeek}, a benchmark for evaluating acquisition-stage privacy leakage of LLM-based agents, with $1{,}182$ cases across $7$ acquisition behaviours and $16$ application domains. Specifically, \emph{Acquisition Inspection} examines the agent's tool-call trajectory, both the tools it invokes and the data it receives, to detect when it acquires sensitive information beyond...
论文介绍 现有针对LLM代理的隐私审计多关注其输出，而忽视了信息获取阶段。本文提出PrivacyPeek基准，专门评估代理在调用工具时过度获取敏感信息的风险。它通过分析代理的工具调用轨迹和接收的数据，判断其是否收集了超出任务必需的信息，为防范隐私泄露提供了新的审计视角和评估工具。
第一作者: Junyoung Park · 方向: AI 安全
越狱攻击记忆注入LLM安全上下文窗口
Abstract:As Large Language Models evolve for user convenience, vulnerability to jailbreak attacks continues to be reported despite ongoing efforts in safety training. Traditional jailbreak techniques typically focus on a single prompt injection, neglecting the models' ability to remember the flow of conversation and the user's instructions. In this paper, we propose Persona Attack, a memory injection based jailbreak method that manipulates the model's context window through a step by step approach. Experimental results from applying Persona Attack to several widely used LLMs reveal that, as injections accumulate in memory, models increasingly prioritize these instructions over their internal safety alignment mechanisms. Furthermore, our experiments empirically demonstrate that the attack success rate varies not only according to the memory implementation of the model, but also...
论文介绍 本文提出Persona Attack越狱方法，利用LLM能够记忆对话历史的特性，通过逐步向模型上下文中注入恶意指令来绕过其安全对齐。研究表明，随着注入指令在记忆中的累积，模型会逐渐优先遵从这些指令而非内部的安全机制。该攻击揭示了依赖对话记忆的LLM所面临的独特安全风险。
第一作者: Ambreen Aslam · 方向: AI 安全
联邦学习物联网入侵检测可解释AI自适应聚合
Abstract:Intrusion Detection Systems (IDS) in Internet of Things (IoT) environments face significant challenges due to data heterogeneity, lack of labeled data, and limited model interpretability. Federated Learning (FL) offers a privacy-preserving solution; however, existing approaches such as SOH-FL suffer from two key limitations: reliance on a manually tuned aggregation parameter {\gamma} and lack of explainability in model predictions. In this paper, we propose XAI-SOH-FL, an enhanced framework that integrates adaptive aggregation and explainable artificial intelligence into the SOH-FL paradigm. First, we introduce a dynamic {\gamma} selection mechanism based on similarity thresholding, enabling the aggregation process to adapt to evolving data distributions. Second, Bayesian Optimization is employed to automatically determine optimal {\gamma} values, eliminating the need for...
论文介绍 针对物联网环境下联邦学习入侵检测系统面临的数据异质性和模型可解释性差的问题，本文提出XAI-SOH-FL框架。该框架在原有SOH-FL基础上，引入基于相似度阈值的动态自适应聚合机制，并利用贝叶斯优化自动确定关键参数，旨在提升模型的实用性和预测的可解释性。
第一作者: Mohan Baruwal Chhetri · 方向: 隐私保护
影子AI关键基础设施AI治理安全风险
Abstract:Frontier AI systems, including large language models and emerging agentic AI tools, offer significant operational benefits but present unique challenges to critical infrastructure (CI) environments due to their non-deterministic and emergent properties. While formal adoption is inherently cautious and tightly controlled due to strict regulatory oversight, widespread accessibility has catalysed shadow AI: the unsanctioned use of frontier AI outside established organisational controls. In CI settings, shadow AI bypasses established assurance and oversight mechanisms, amplifying risks to data protection, decision reliability, and regulatory compliance, with potential consequences for essential service delivery. We present the first empirical study of shadow AI in CI environments, characterising it as a systemic socio-technical condition of assurance erosion. Drawing on...
论文介绍 前沿AI工具在带来效益的同时，也催生了在关键基础设施环境中未经批准、脱离组织控制的「影子AI」使用现象。本文将其定义为一种侵蚀保障和安全的系统性社会技术状况，并基于实证研究指出，这种无监督的使用会显著增加数据保护、决策可靠性和合规性方面的风险。
第一作者: Manik Kumar Sangala · 方向: 密码学协议
量子计算后量子密码学安全综述量子威胁
Abstract:Quantum computing has emerged as a transformative computing paradigm capable of solving problems that remain computationally infeasible for classical systems; however, its rapid advancement also introduces significant security, privacy, and reliability concerns. In this context, this survey presents a comprehensive review of security challenges and mitigation strategies associated with quantum computing, focusing on security issues in quantum computers, security threats caused by quantum computers, and security mechanisms developed for quantum systems. The paper examines vulnerabilities in quantum hardware and software, the impact of quantum computing on existing cryptographic infrastructures and cybersecurity mechanisms, and the development of quantum-resilient solutions such as post-quantum cryptography, quantum-safe communication protocols, quantum intrusion detection...
论文介绍 本综述系统梳理了量子计算带来的安全挑战与应对策略。内容涵盖量子计算机自身的安全漏洞、其对现有密码体系和网络安全机制的威胁，以及后量子密码学、量子安全通信协议等量子韧性解决方案的最新发展，为理解量子时代的安全 landscape 提供了全面参考。
第一作者: Farhin Farhad Riya · 方向: 系统安全
差分隐私联邦学习隐私推理攻击数据异质性
Abstract:Heterogeneous Differential Privacy (HDP) in Federated Learning (FL) allows clients to select individual privacy budgets ($\varepsilon_i$) according to institutional policies and data sensitivity. In practice, many HDP-FL systems employ $\varepsilon$-aware server aggregation to improve model utility by re-weighting client updates according to their declared privacy budgets. However, gradient updates in FL retain structural patterns induced by non-independent and identically-distributed (non-IID) data, and these additional signals exposed by $\varepsilon$-aware aggregation create new opportunities for inference by an honest-but-curious server. In this work, we first show that a server equipped with gradient denoising and surrogate modeling can mount a \emph{Privacy Inference Attack} that infers distributional attributes of clients and links updates from the same client across...
论文介绍 在允许客户端自选隐私预算的异构差分隐私联邦学习中，服务器的加权聚合策略可能泄露信息。本文揭示了一种隐私推理攻击：诚实但好奇的服务器可利用梯度去噪和代理建模，从聚合的梯度更新中推断客户端的数据分布属性，并跨轮次链接同一客户端的更新。
第一作者: Felix Reichmann · 方向: 软件安全
软件物料清单组件包含机制软件供应链安全SBOM生成工具
Abstract:By listing the components included in an application, Software Bills of Materials (SBOMs) are intended to support the timely identification of vulnerable components and ensure the security of the software supply chain. However, we question the underlying assumption that there is agreement on the components to be listed in an SBOM and that current technology is sufficient to secure the software supply chain. First, we propose a ground-up analysis of Component Inclusion Mechanisms (CIM) in the software's development lifecycle. Then we systematically analyze the four popular SBOM generation tools, cdxgen, syft, trivy, ORT, and the Microsoft sbom-tool, to understand how they define and identify relevant components. Finally, we assess these using a ground truth across the programming languages Python, Java, Go, PHP, Rust, and C. While today's tools are a step toward identifying...
论文介绍 软件物料清单（SBOM）旨在标识漏洞组件以保障软件供应链安全，但其前提是组件定义一致且当前技术足够。本文从底层分析了软件开发生命周期中的组件包含机制，并系统评估了cdxgen、syft、trivy等主流SBOM生成工具如何定义和识别组件。研究通过跨语言的基准真值测试，揭示了当前工具的局限性，强调了建立对组件的共同理解对SBOM有效性的关键作用。
第一作者: Yuxin Liu · 方向: 隐私保护
信息共享隐私保护寡头竞争库尔诺模型
Abstract:Information sharing among competing suppliers can improve decision-making under uncertainty, yet strategic concerns regarding rival exploitation often deter voluntary disclosure. We study information-sharing mechanisms in a Cournot oligopoly with uncertain demand, where a platform aggregates suppliers' signals through privacy-preserving channels and may also possess an exogenous external signal. The central challenge is to balance strategic safety with informational utility: privacy noise reduces the exposure of individual signals, but also lowers the value of the shared information pool. We first characterize a baseline setting in which access to aggregated information is contingent on participation. In a two-firm market without an external signal, firms refuse to share regardless of the privacy level. In an \(n\)-firm market, sharing may arise even without privacy safeguards...
论文介绍 本文研究寡头竞争市场中供应商之间的信息共享机制。面对不确定的需求，竞争对手的战略顾虑常阻碍信息自愿披露。研究构建了一个库尔诺寡头模型，平台通过隐私保护通道聚合供应商信号，并可能拥有外部信号。核心挑战在于平衡战略安全与信息效用：隐私噪声虽保护个体信号，但也降低共享信息池的价值。研究分析了不同市场结构和隐私水平下信息共享出现的条件。
第一作者: Lucien Martial · 方向: 软件安全
连续变量量子密钥分发多维协调纠错码开源仿真
Abstract:Continuous-variable quantum key distribution (CV-QKD) requires highly efficient reconciliation techniques to operate at low signal-to-noise ratios and long distances. Multidimensional reconciliation addresses this challenge by transforming the physical Gaussian quantum channel into a virtual binary-input additive white Gaussian noise (BIAWGN) channel, enabling the use of modern errorcorrecting codes. In this work, we review the principles of multidimensional reconciliation, with a particular focus on high-dimensional constructions beyond the algebraic dimensions 1, 2, 4, 8. We describe the construction of the virtual channel, discuss practical coding schemes for reverse reconciliation, and analyse their integration with linear error-correcting codes. We also present an opensource simulation framework, HDirac, implementing multidimensional reconciliation for arbitrary...
论文介绍 连续变量量子密钥分发（CV-QKD）需要高效的协调技术以在低信噪比和长距离下运行。多维协调通过将高斯量子信道转换为虚拟二进制输入加性高斯噪声信道来解决此问题，从而能利用现代纠错码。本文综述了多维协调原理，特别关注超越代数维度1、2、4、8的高维构造，描述了虚拟信道构建、实际编码方案，并介绍了用于任意维度仿真的开源框架HDirac。
第一作者: Peihan Liu · 方向: 安全研究
差分隐私合成文本能力评估基准测试
Abstract:Differentially private (DP) text synthesis promises to unlock sensitive corpora for model training, but it remains unclear whether DP synthetic data transmits genuinely new knowledge and capabilities present only in those corpora. This is because existing evaluations rely on tasks that are nearly solvable without training, so strong benchmark performance does not establish that DP synthesis can substitute original data access. Thus, we introduce ContinuousBench, a continuously and automatically-regenerated benchmark that measures capability gain from DP synthetic text. Each quarter, a new release pairs a never-before-seen training corpus with a derived QA set, constructed to be: (1) unsolvable sans-corpus; and (2) learnable under DP, as the tested knowledge is supported by hundreds of independent records. Researchers produce DP synthetic data from the training corpus and run...
论文介绍 差分隐私（DP）合成文本有望解锁敏感语料库用于模型训练，但现有评估依赖的任务本身无需训练即可近似解决，因此无法证明DP合成数据能传递原始语料独有的新知识。本文引入ContinuousBench，一个可连续自动更新的基准，用于衡量DP合成文本带来的能力增益。该基准每季度发布一个从未公开的训练语料及其派生问答集，要求所测试知识可被DP学习且无法在无语料时求解。
第一作者: Rakshit Naidu · 方向: AI 安全
分布推断攻击公平微调均等几率约束隐私保护
Abstract:Machine learning models trained on sensitive data can inadvertently leak population-level information about their training distributions -- a threat known as distribution inference attack (DIA). An adversary with black-box access can infer sensitive demographic properties, such as subgroup proportions, without observing any training data directly. While defenses such as differential privacy and property unlearning have been proposed, the link between fairness constraints and distributional leakage remains unexplored. We propose Fair Fine-tuning (FFt): a trained model is fine-tuned on samples from the complementary distribution under an Equalized Odds (EO) constraint. We provide a complete theoretical characterization, proving the tight bound $\text{Adv}(\mathcal{A},M_f) \le \Delta_{\text{EO}} \cdot W$, where $W$ quantifies how distinguishable the two training distributions are...
论文介绍 机器学习模型可能泄露其训练数据分布的群体信息，这被称为分布推断攻击（DIA）。本文提出公平微调（FFt）作为防御手段：在均等几率（EO）约束下，使用互补分布的样本对训练好的模型进行微调。研究提供了完整的理论刻画，证明了攻击优势的紧上界，该上界与两个训练分布的可区分度及公平约束违反程度相关，首次建立了公平性与分布隐私泄漏之间的联系。
第一作者: Matthew Regehr · 方向: 安全研究
机器遗忘平滑强凸损失风险界限统计优化
Abstract:Machine unlearning is motivated by legal and user-facing requirements to remove the influence of individuals' data from trained models, such as the right to be forgotten. Prior work has developed algorithms and error bounds for unlearning in smooth strongly convex stochastic optimization, but the fundamental statistical cost of unlearning has remained unclear. We nearly resolve this problem by proving upper and lower bounds on the excess population risk of approximate $\varepsilon$-unlearning; our bounds are tight up to a condition-number factor. For mean estimation over the unit ball, our upper and lower bounds match. The optimal rate is the usual statistical error plus an unlearning penalty that interpolates between the retraining-from-scratch rate and an exponentially smaller term as $\varepsilon/d$ grows, where $d$ is the dimension of the model. In particular, when...
论文介绍 机器遗忘旨在满足法律和用户需求，从训练模型中移除个体数据的影响。针对平滑强凸随机优化问题，本文几乎完全解决了遗忘的基本统计成本问题。研究证明了近似ε-遗忘的种群风险的上下界，在均值估计问题中界限匹配。最优误差是常规统计误差加上一个遗忘惩罚项，该惩罚项随着ε/d的增大，在从头再训练速率和指数级更小的项之间插值。
第一作者: Qi Hu · 方向: 软件安全
LLM编码代理操作安全基准测试安全违规
Abstract:Large language models are increasingly deployed as coding agents, shifting safety from individual responses to action sequences. Existing benchmarks, however, primarily assess whether models refuse unsafe prompts, leaving impacts on stateful workspaces largely unexamined. We present SABER, a benchmark for environment-aware operational safety that places models in realistic agent-style projects and evaluates safety from the final environment state after a sequence of actions. Beyond binary safety-violation reports, SABER categorizes violations by cause, enabling analysis of model-specific safety profiles. Our evaluations show that even the best-performing model has more than a 54% harmful safety-violation rate (HSR), suggesting that current alignment remains insufficient for realistic project environments. SABER further reveals distinct safety profiles across models. Our...
论文介绍 大语言模型作为编码代理部署时，安全性评估需从单条响应转向行动序列。现有基准主要评估模型是否拒绝不安全提示，而忽视了行动对有状态工作空间的影响。本文提出SABER基准，将模型置于真实的代理式项目环境中，根据一系列行动后的最终环境状态来评估环境感知的操作安全。评估发现，即使表现最佳的模型也有超过54%的有害安全违规率，揭示了当前对齐方法的不足。
第一作者: Donghwa Seo · 方向: 网络安全
区块链交易费用优先队列博弈论
Abstract:This paper analyzes transaction fees on blockchains by considering that they form a priority queue and users play a queueing game. Using an M/G^K/1 priority queue model, we provide new insights into the dynamics governing transaction fees and their impact on user behavior. We derive semi-closed form expressions for steady-state quantities and extend the relationship between user delay costs and transaction fees to general block generation times. We apply the model to the Bitcoin network and simulate user responses under various scenarios. Cross-chain analysis across Bitcoin, Dogecoin, and Litecoin reveals similarities in normalized cost structures.
论文介绍 本文将区块链中的交易费用视为优先队列，用户进行排队博弈。研究采用M/G^K/1优先队列模型，为交易费用动态及其对用户行为的影响提供了新见解。推导了稳态量的半封闭表达式，并将用户延迟成本与交易费用之间的关系扩展至一般的区块生成时间。模型被应用于比特币网络，并在各种情景下模拟用户响应。跨链分析揭示了比特币、狗狗币和莱特币在归一化成本结构上的相似性。
第一作者: Yuyang Gong · 方向: 软件安全
检索增强生成对抗性攻击语篇操纵安全黑盒
Abstract:Retrieval-Augmented Generation (RAG) systems are widely deployed and increasingly influential, but their reliance on external corpora exposes new security risks from poisoned retrieval content. Existing RAG attacks are largely focusing on individual queries or narrow topic-local query sets, which limits their practical reach and offers limited camouflage in real-world settings. In this paper, we introduce discourse-level opinion manipulation, a new threat model in which coordinated influence across a semantic query network induces opinion shifts over a holistic, multi-topic query space. We formalize this threat in a black-box setting and propose DiscourseFlip, an agentic, graph-guided attack that dynamically allocates a limited poisoning budget to maximize discourse-level opinion deviation. Extensive experiments demonstrate that DiscourseFlip consistently induces targeted...
论文介绍 该研究关注检索增强生成系统的安全威胁，指出其对外部语料库的依赖会引入投毒风险。现有的攻击主要针对单个或狭窄主题的查询。本文提出了一种新的威胁模型「语篇级观点操纵」，即通过在语义查询网络中施加协调影响，诱导整个多主题查询空间的观点偏移。为此，作者提出了名为 DiscourseFlip 的智能体攻击方法，该方法在黑盒设定下，动态分配有限的投毒预算以最大化语篇级的观点偏离。
第一作者: Nuh Aydin · 方向: 软件安全
平方乘算法算法历史密码学计算数论
Abstract:The square-and-multiply algorithm, also known as binary exponentiation or repeated squaring, is a technique for fast exponentiation commonly used in modern cryptography and computational number theory. Despite its prominence, the historical origins of the algorithm are not known with certainty. This paper critically examines the origins and formalization of the algorithm through primary source analysis. We focus on Jamshid al-Kashi's fifteenth-century Miftah al-Hisab where the algorithm is articulated explicitly as a general method and claimed by al-Kashi as his own innovation. To contextualize this, we trace earlier instances of successive squaring in the works of al-Uqlidisi and al-Biruni, who applied these techniques for specific calculations, but did not formalize them into a general procedure. The earliest known work on this method of computation is found in Pingala's...
论文介绍 平方乘算法（也称为二进制指数运算或重复平方法）是现代密码学和计算数论中用于快速幂运算的常用技术，但其确切的历史起源并不明确。本文通过分析原始文献，批判性地考察了该算法的起源与形式化过程。研究重点聚焦于 15 世纪波斯数学家 Jamshid al-Kashi 的著作，其中明确将该算法作为一种通用方法阐述。文章还将早期 al-Uqlidisi 和 al-Biruni 等人工作中出现的连续平方技术作为背景进行追溯。
第一作者: Rana Muhammad Usman · 方向: 密码学协议
大语言模型智能体对抗性信息流安全评估决策偏见
Abstract:LLM agents increasingly act after consuming ranked external information streams such as social feeds, search results, retrieval contexts, and email queues, yet safety evaluations almost always test the model or the user prompt in isolation, never the upstream ranker that decides what the agent reads just before it acts. We introduce a controlled protocol that holds the model, persona, topic, and final decision prompt fixed and varies only the composition and ordering of the posts an agent encounters during a preceding ten-turn "scrolling" phase, isolating the causal effect of feed curation on a downstream decision. Across 2,785 decision rollouts on four modern open instruct LLMs from three independent labs, we identify three response regimes: adversarial capitulation, default saturation, and a default-direction asymmetry in which a one-sided feed tips a decision the model was...
论文介绍 大语言模型代理在行动前会处理来自外部信息流（如社交动态、搜索结果）的内容，但安全评估通常孤立测试模型或提示，忽略了上游信息排序器的影响。本文提出一个控制实验协议，在固定模型、角色、主题和最终决策提示的前提下，仅变化代理在「滚动浏览」阶段所接触内容的构成和顺序，从而隔离信息流编排对下游决策的因果效应。实验发现存在三种响应模式，揭示了对抗性信息流对代理决策的潜在操纵能力。
第一作者: Yu-An Lu · 方向: 软件安全
推理追踪安全隐私大语言模型知识蒸馏
Abstract:Reasoning traces have become a valuable form of learning signals for improving and transferring the capabilities of large language models. In particular, detailed traces can help distill reasoning behavior from stronger teacher models into weaker student models. The value of capability transfer has motivated many deployed systems with reasoning models to hide raw internal traces and expose at most summaries and answers to users. As a result, we ask whether such interface-level trace hiding prevents users from obtaining useful reasoning supervision through prompting. We study this question with Reasoning Exposure Prompting (REP), a lightweight in-context elicitation method that uses shadow-model-generated demonstrations wrapped in auxiliary code-like formats to raise user-visible reasoning traces from a victim model. Across the common reasoning dataset, different victim models...
论文介绍 推理追踪是提升和迁移大语言模型能力的重要学习信号。一些部署系统会隐藏模型的内部推理追踪，仅向用户展示摘要和答案。本文旨在研究这种界面级的追踪隐藏是否能阻止用户通过提示获取有用的推理监督。为此，作者提出了一种名为「推理暴露提示」的轻量级上下文引导方法，利用辅助代码格式包装的演示，诱导受害模型产生用户可见的推理追踪。
第一作者: Mohammed Sameer Syed · 方向: AI 安全
工具使用模型安全不对称性攻击面安全评估
Abstract:As language models take on agentic roles that span calling external APIs, reading tool outputs, and acting on instructions embedded in third-party content, their attack surface expands well beyond what users type. Whether a model treats a malicious instruction the same way regardless of where it arrives has not been systematically studied. We introduce the Safety Asymmetry Score (SAS), which measures how much a model's susceptibility to adversarial content shifts depending on whether that content arrives in the user message, tool metadata, or tool output, using matched payload pairs that keep the malicious text identical and vary only the context of delivery. Evaluated across 6 production LLMs and three attack families, we find a consistent and informative asymmetry: agent-native models are substantially more vulnerable when adversarial content arrives via tool descriptions...
论文介绍 随着语言模型承担智能体角色并调用外部工具，其攻击面扩展到了用户输入之外。本文研究了模型是否对来自不同渠道（用户消息、工具元数据、工具输出）的恶意指令表现出相同的脆弱性。研究引入了「安全不对称性评分」，通过匹配的有效载荷对（恶意文本相同，仅投递上下文不同）来衡量模型的易感性变化。评估发现，智能体原生模型在对抗性内容通过工具描述到达时，明显更脆弱。
第一作者: Su Wang · 方向: AI 安全
技能组合代理安全风险评估基准测试
Abstract:LLM agents increasingly rely on community-contributed skills that expand an agent's operational capability set. We study a core safety problem in agentic AI systems: whether individually safe skills can compose into unsafe installed skill sets. We present SkillReact, a compositional security measurement framework with three components: a deterministic static-composition benchmark, a two-rater LLM-assisted human-adjudication pipeline, and an action-based exploitability harness. On 1,520 ClawHub skills, 651 pass individual inspection and form 211,575 pairs; the benchmark flags 22.25% of these as structural candidates. We treat this raw rate as a recall-oriented scanner ceiling and calibrate it against human judgment: in a pattern-stratified audit, roughly one in five flagged pair-pattern hits survives as a real compositional risk (population-weighted validity 18.2%, our headline...
论文介绍 大语言模型代理日益依赖社区贡献的技能来扩展能力。本文研究了智能体 AI 系统中的一个核心安全问题：单独安全的技能在组合后是否会产生不安全的技能集合。研究提出了一个名为 SkillReact 的组合安全性度量框架，包含静态组合基准、人机协同仲裁流程和基于动作的可利用性测试套件。在对大量技能对进行分析后，发现约五分之一的标记组合模式确实构成真实的组合风险。
第一作者: Thomas Humphries · 方向: 安全研究
差分隐私k均值聚类私有演化数据安全
Abstract:We study the problem of differentially private (DP) $k$-means clustering in Euclidean space. Previous solutions rely on summing the private data directly, which induces a sensitivity proportional to the domain. We introduce PE-means, an extension of the private evolution (PE) algorithm (an increasingly popular method for synthetic data generation), to the problem of $k$-means clustering. The key advantage of PE is that it only computes a private histogram with constant sensitivity to guide the evolution. Our adaptation of PE includes new evolutionary operators for clustering, as well as other algorithmic improvements of independent interest. Overall, PE-means achieves an average improvement of 20% in clustering loss over state-of-the-art baselines.
论文介绍 本文研究了欧氏空间中的差分隐私 k 均值聚类问题。先前的解决方案直接对私有数据求和，其灵敏度与数据域相关。作者提出了 PE-means 算法，它是私有演化算法（一种日益流行的合成数据生成方法）在 k 均值聚类问题上的扩展。PE 的关键优势在于仅计算一个具有恒定灵敏度的私有直方图来指导演化过程。实验表明，PE-means 的聚类损失相比现有先进基线平均提升了 20%。
第一作者: Jonghyun Chung · 方向: AI 安全
生成式AI数字生态主动检测生命周期
Abstract:The proliferation of adversarial synthetic content, accelerated by Generative AI (GenAI) is rendering traditional reactive detection methods ineffective. This survey synthesizes emerging research to demonstrate a paradigm shift toward the proactive detection of emerging inauthentic narratives. In this survey, we adopt a unified, lifecycle-based taxonomy to combine socio-technical lifecycle models of adversarial campaigns with advanced computational methodologies for emerging inauthentic narrative detection. By structuring the analysis around the C5 Interaction Model (Context, Causes, Content, Cycle of Amplification, Consequences), we integrate different research streams from machine learning and social science. To differentiate spread patterns of synthetic amplification from authentic baseline traffic, this paper surveys state-of-the-art techniques for modeling the creation...
论文介绍 生成式AI加速了对抗性合成内容的泛滥，使得传统的被动检测方法失效。本综述总结了新兴研究，旨在展示一种向主动检测新兴非真实叙事转变的范式。文章采用统一的、基于生命周期的分类法，将对抗性运动的社会技术生命周期模型与新兴叙事检测的先进计算方法相结合。通过围绕「C5 交互模型」构建分析，该综述整合了来自机器学习和社会科学的不同研究流。
第一作者: Olga E. Sorokoletova · 方向: AI 安全
大语言模型对齐安全性自我恢复
Abstract:Responsible AI initiatives place great emphasis on the safety of Large Language Model (LLM)-based systems. In particular, it has become standard practice to subject these models to an alignment procedure aimed at preventing harmful outputs. However, once aligned, a model is not guaranteed to maintain this alignment throughout its lifecycle. Moreover, the likelihood of misalignment increases as malicious actors may deliberately employ jailbreaking techniques to compromise LLM safety. To counter this, much research has focused on improving alignment methods and post-processing filters. In this paper, we introduce a new perspective on advancing LLM alignment: rather than developing stronger alignment techniques, we investigate the model's intrinsic ability to recover its alignment after corruption. We propose a methodology for modeling the safety trajectories of user-assistant...
论文介绍 本文针对大语言模型（LLM）在对齐后可能因恶意攻击或意外而偏离安全准则的问题，提出了一种新视角。研究者不聚焦于强化对齐技术本身，而是探究模型在对齐被破坏后的内在恢复能力。他们提出了一种模拟用户-助手安全交互轨迹的方法论，旨在建模并评估LLM从不安全状态自我修正的潜力，这对构建更具韧性的安全AI系统具有重要意义。
第一作者: Junjie Ye · 方向: 导航与运动 · 来源: cs.RO
机器人学习数据合成世界模型组合泛化
Abstract:Scaling robot learning requires large-scale, diverse demonstrations, yet real-world data collection via teleoperation remains prohibitively expensive and time-consuming. While video diffusion models offer a promising avenue for data scaling, existing generative approaches are often limited to superficial visual augmentation, or suffer from embodiment hallucinations that yield physically infeasible motions. We present a generalizable embodiment-centric world model that achieves scalable data generation by synthesizing photorealistic demonstrations with novel objects, in novel scenes, and from novel viewpoints. Our approach anchors generation to rendered robot motion while conditioning on explicit scene and object priors, effectively decoupling trajectory execution from environment synthesis. This formulation has the potential to unlock two powerful data scaling capabilities...
论文介绍 大规模机器人学习依赖于丰富多样的示范数据，但真实世界采集成本高昂。现有视频生成方法常局限于视觉增强或产生物理不可行的运动。本文提出了一个以实体为中心、可组合的世界模型，通过合成逼真的演示数据来应对数据规模化的挑战。该模型能在新物体、新场景和新视角下生成数据，通过解耦运动轨迹与环境合成，有望实现强大的数据缩放能力，加速机器人技能学习。
第一作者: Haimin Hu · 方向: 具身智能 · 来源: cs.RO
机器人安全安全滤波器信念空间可验证性
Abstract:Autonomous robots that interact with people must make safe and efficient decisions under human-induced uncertainty, such as their preferences, goals, competency, and willingness to cooperate. Safety filters are a popular approach for ensuring safety in interactive robotics, since their modular design separates safety from performance, allowing robots to operate safely around people with minimal impact on task efficiency. While traditional safety filters typically operate only in the physical space, neglecting the robot's ability to learn and adapt online, the recently proposed belief-space safety filter (BeliefSF) reasons about robot safety in closed-loop with runtime inference that actively reduces the robot's uncertainty online, thereby reducing conservativeness in filtering. However, providing formal safety guarantees for robots deploying BeliefSF remains a significant...
论文介绍 在与人交互的自主机器人领域，需在人类意图不确定的情况下做出安全决策。安全滤波器是一种将安全性与性能模块化的方法。本文关注提升信念空间安全滤波器的可验证性。该滤波器能在线进行闭环推理，以减少保守性。然而，为其提供形式化的安全保证仍是挑战。本文提出了可验证的信念空间神经安全滤波器，旨在为部署于动态交互环境中的机器人提供更可靠的安全保障。
第一作者: Zhaoning Wang · 方向: 机器人操作 · 来源: cs.RO
可供性基础模型机器人操作功能理解
Abstract:Affordance understanding bridges visual perception and physical action, serving as an explainable interface for robot manipulation in open and unstructured real-world environments. Yet, building an affordance foundation model that not only understands where and how the interaction should happen, but also generalizes across diverse environments, objects, and tasks, remains a long-standing research challenge. Existing methods typically address only part of this challenge, either localizing task-relevant regions without specifying executable motion, or predicting motion but with limited scalability. In this paper, we present ourmodel, a step towards an affordance foundation model for functionality understanding. From a single RGB-D observation and a language task description, ourmodel predicts a task-conditional functional mask (where to interact) and a 3D post-contact motion...
论文介绍 可供性理解是连接视觉感知与物理动作的桥梁，对机器人操作至关重要。构建一个能泛化至多样环境、物体和任务的可供性基础模型仍是难题。现有方法通常只解决部分挑战。本文提出了一个模型，作为构建功能理解可供性基础模型的一步。该模型能从单张RGB-D图像和语言描述出发，预测任务条件的交互区域（在哪里交互）以及三维接触后运动（如何交互）。
第一作者: Xiaobei Zhao · 方向: 导航与运动 · 来源: cs.RO
农业机器人视觉语言导航指令错误基准测试
Abstract:Agricultural robots are serving as powerful assistants across a wide range of agricultural tasks, nevertheless, still heavily relying on manual operations or railway systems for movement. The AgriVLN method and the A2A benchmark pioneeringly extended Vision-and-Language Navigation (VLN) to the agricultural domain, enabling a robot to navigate to a target position following a natural language instruction. However, almost all the prior methods adopt an ideal assumption that the given instructions themselves are correct, which does not align with the realistic scenarios, because anybody may say an instruction with mistakes. To bridge this gap, we propose the A2A-MI benchmark, in which we build a semi-automatic data annotator to insert three mistake classifications into each original instruction in a more diversified and efficient way. We test several state-of-the-art agricultural...
论文介绍 农业机器人正从手动或轨道系统向智能自主导航发展。视觉语言导航被引入农业领域，但现有方法均假设指令本身正确，这与现实不符。为弥补这一缺陷，本文提出了新的基准测试，在原始指令中插入三类错误。同时，研究者测试了前沿的农业导航智能体，并提出了一种错误检测方法，旨在提升智能体在面对不完美或错误指令时的鲁棒性。
第一作者: Shahram Najam Syed · 方向: VLA 通用模型 · 来源: cs.RO
视觉语言动作模型动态操作世界模型预测控制
Abstract:Vision-Language-Action (VLA) models generalize across static manipulation but fail when objects move during task execution. They map the current observation to an action and assume the scene is stationary between observation and execution, so at any non-trivial object speed the resulting latency exceeds the time available to grasp. We close this gap with AHEAD (Anticipatory Horizon Extrapolation with Adaptive Dynamics), a predict-then-act wrapper that augments a frozen VLA with a motion-aware latent world model. A small world model trained on manipulation video forecasts future patch tokens in the VLA's feature space, conditioned on per-token velocity and acceleration from optical flow. A language-and-motion saliency mask concentrates prediction on task-relevant patches, and the model rolls forward for an adaptive horizon, halting when prediction uncertainty crosses a...
论文介绍 视觉语言动作模型在静态操作任务上表现良好，但物体移动时会因感知与执行间的延迟而失效。本文提出了一种「先预测、后行动」的框架来弥合这一差距。该框架利用一个运动感知的潜在空间世界模型来预测未来观测，为冻结的VLA模型提供补偿。通过语言与运动显著性掩码聚焦于任务相关区域，并根据预测不确定性自适应确定预测时域，从而实现对动态物体的精确操作。
第一作者: Tianyang Chen · 方向: VLA 通用模型 · 来源: cs.RO
无人机视觉语言动作模型强化学习意图对齐
Abstract:Vision-Language-Action (VLA) models offer a promising end-to-end paradigm for unmanned aerial vehicles (UAVs) to accomplish complex tasks specified by fine-grained instructions. However, standard supervised fine-tuning (SFT) suffers from data scarcity, limited generalization, and weak supervision for nuanced and complicated human intents. Reinforcement fine-tuning offers a natural way to mitigate these challenges and align policy behaviors with human intents through designable feedback, but applying it to aerial navigation remains challenging due to inefficient exploration in expansive continuous spaces. To address these challenges, we introduce an efficient reinforcement learning (RL) framework for VLA-based aerial navigation. At its core, we propose EG-GRPO (Expert-Guided Group Relative Policy Optimization) to augment online rollouts with few-shot expert data. Additionally...
论文介绍 视觉语言动作模型为无人机执行复杂任务提供了端到端范式，但标准监督微调面临数据稀缺和泛化能力不足的问题。强化微调虽能通过反馈对齐人类意图，但在广阔的连续空间中探索效率低下。本文针对无人机空中导航任务，提出了一种高效的强化学习框架。其核心是专家引导的群组相对策略优化方法，通过融合少量专家数据来增强在线探索，以更精确地对齐复杂的人类意图。
第一作者: Arusa Kanwal · 方向: VLA 通用模型 · 来源: cs.RO
视觉语言动作模型评估失败发现测试生成
Abstract:Vision-Language-Action (VLA) models are increasingly used as generalist robot policies, yet their evaluation still relies largely on static benchmarks that randomly sample task scenes. In high-dimensional embodied spaces, failures are sparse and clustered, so static benchmarking can underestimate robustness risks. We reframe VLA evaluation as an active failure-discovery problem and propose a failure-aware test-generation approach that combines diversity-driven exploration with surrogate models learned from observed executions. The method steers testing toward high-risk yet diverse scene regions. Across four state-of-the-art VLA models, it uncovers substantially more failures (up to +29.7 % over selected baselines) while revealing more diverse failure modes. This mean that, for instance, in the case of GR00T-N1.6, success rate dropped from 64.4% to 34.7%. More broadly, our...
论文介绍 当前对视觉语言动作模型的评估大多依赖于静态随机采样的基准，这可能低估了其鲁棒性风险，因为失败往往是稀疏且聚集的。本文将评估重新定义为一个主动的失败发现问题，提出了一种失败感知的测试生成方法。该方法结合了多样性驱动的探索和从历史执行中学习到的代理模型，能够引导测试走向高风险但多样的场景区域，从而更有效地揭示VLA模型的潜在失败模式。
第一作者: Alkesh K. Srivastava · 方向: 具身智能 · 来源: cs.RO
多机器人系统信息传播动力学遭遇通信目标跟踪信息年龄
Abstract:Multi-robot systems cannot assume persistent network connectivity. We study this problem through target tracking, where performance depends on how quickly target information is sensed, transported through the team, and used before it becomes stale. When robots exchange information only through physical encounters, tracking becomes a kinetic information-transport problem: robot motion induces encounters, encounters carry target-state estimates, information age determines staleness, and stale information produces tracking error. This paper develops a kinetic theory of encounter-based information propagation and identifies three limits. The first is an access limit -- information cannot support team-level coordination unless it spreads beyond the robots that sensed it. The second is a staleness limit -- even propagated information loses value as the target moves. The third is a...
论文介绍 本文研究多机器人系统在无持久网络连接下通过物理接触进行信息传播的问题，以目标跟踪为应用场景。分析了机器人运动引发遭遇、遭遇携带状态估计、信息年龄决定新鲜度以及过时信息导致跟踪误差的动态过程。提出了基于遭遇的信息传播动力学理论，明确了访问限制、过时限制等核心约束，为优化多机器人团队的信息共享和协调提供了理论框架。
第一作者: Zhiming Xu · 方向: 导航与运动 · 来源: cs.RO
强化学习动态适应零样本学习潜在动态对比学习
Abstract:Real-world dynamics shifts pose a critical challenge for reinforcement learning in robotics, as policies tightly coupled to nominal environments often fail catastrophically when physical conditions change. Most existing methods rely on encoding explicitly identified physical parameters into a latent context, a parameter-centric paradigm that depends on pre-specified axes of variation and becomes brittle under unmodeled or compound dynamics changes. We revisit dynamics adaptation from an outcome-centric perspective: rather than telling policies what the dynamics are, we enable them to learn how dynamics affect interaction outcomes. Theoretically, this is grounded in a monotonic relationship between target-domain regret and the Lipschitz constant of a trajectory dynamics encoder. Practically, this constant can be upper-bounded through contrastive learning, yielding a smooth...
论文介绍 针对机器人强化学习中环境动态变化导致策略失效的问题，本文提出一种半监督方法来发现潜在动态几何结构。通过从结果中心视角出发，利用对比学习约束动态编码器的Lipschitz常数，使策略能够在未见过的动态条件下实现零样本适应，从而提升模型对未建模或复合动态变化的泛化能力。
第一作者: Bin Yu · 方向: VLA 通用模型 · 来源: cs.RO
视觉-语言-动作模型语义接地动作预测基准测试VLA
Abstract:Vision-language-action (VLA) models are built on the premise that semantic understanding from pretrained language or vision-language backbones should guide robot action prediction. Yet robot fine-tuning is optimized as imitation over task-specific action distributions, and many evaluations can be solved through visual or instruction-action shortcuts. We introduce RoboSemanticBench (RSB), an embodied benchmark for diagnosing semantic grounding in action prediction: whether post-trained VLA models can use complex instruction semantics to select and manipulate the correct physical target. In each episode, a robot receives a multiple-choice math or general-knowledge question, observes candidate answer blocks, and must grasp the block corresponding to the correct answer. RSB covers controlled arithmetic, grade-school mathematical understanding, and commonsense or factual...
论文介绍 本文提出RoboSemanticBench基准，用于诊断视觉-语言-动作模型在动作预测中的语义接地能力。通过让机器人根据多选题选择正确答案块，评估模型对复杂指令语义（如算术和常识问题）的理解和应用，旨在揭示模型是否真正利用语义信息指导物理操作，为VLA模型的改进提供评估工具。
第一作者: Huayi Zhou · 方向: 机器人操作 · 来源: cs.RO
机器人操作3D表示视觉语言模型对齐学习泛化策略
Abstract:End-to-end manipulation policies, combined with web-scale pretrained Vision-Language Models (VLMs), show the promise for generalizable and dexterous robotic manipulation. However, they inherit two key limitations from 2D foundation models: 1) the reliance on 2D RGB inputs that ignores the intrinsically 3D nature of manipulation; and 2) the lack of spatial 3D alignment between input-output spaces as well as across diverse robot embodiments, camera setups, and trajectory datasets. In this paper, we present a series of contributions to address these issues. First, we introduce aligned vertex map and vertex spectrum -- a pixel-wise 3D representation that elevates 2D visual inputs to 3D, using camera calibration and optional depth. This novel input representation marries 3D awareness with the generalization of 2D large VLMs. Then, we propose to align the inputs and outputs of...
论文介绍 针对端到端操作策略依赖2D输入的局限性，本文提出Dexterity-BEV方法。通过引入对齐顶点图和顶点谱，将2D视觉输入提升为像素级3D表示，实现输入输出空间以及跨机器人本体、相机设置和轨迹数据集的3D对齐，从而增强策略的泛化能力和对灵巧操作的支持。
第一作者: Adnan Harun Dogan · 方向: 具身智能 · 来源: cs.RO
状态估计卡尔曼滤波器频率加权神经网络噪声抑制
Abstract:Robust state estimation is central to robotic autonomy, yet classical Kalman filters struggle with frequency-dependent disturbances and model mismatch such as sensor vibrations, electromagnetic interference, and periodic noise. Although Deep Kalman Filter (DKF) variants extend the Extended Kalman Filtering (EKF) framework by learning latent transitions, they lack explicit mechanisms to suppress band-limited noise components that typically corrupt sensor measurements in real-world scenarios. We introduce the Frequency-Weighted Neural Kalman Filter (FW-NKF), a unified hybrid approach that embeds a causal spectral-shaping operator into the Kalman measurement residual and jointly learns observation, and transition networks. By adapting both the filter spectrum and the latent state representation, FW-NKF attenuates the noise-dominated frequency bands while capturing complex...
论文介绍 本文提出频率加权神经卡尔曼滤波器FW-NKF，用于改善机器人状态估计中频率依赖干扰和模型失配问题。通过在卡尔曼滤波残差中嵌入因果频谱整形算子，并联合学习观测和转移网络，自适应抑制传感器噪声主导的频带，从而提升估计的鲁棒性，适用于复杂真实场景。
第一作者: Eduardo Sebastián · 方向: 具身智能 · 来源: cs.RO
机器人学习因子化泛化世界模型任务模型
Abstract:Robot learning must produce policies that generalize to new combinations of constraints, teammates, and environments. To achieve this, we must structurally factor the policy, which is a choice that dictates what generalizes, what requires retraining, and what remains entangled. Existing methods span a wide spectrum, from expecting structure to emerge from data scaling, to hand-designing it via hierarchies, skill libraries or learned specializations. In this paper, we study what we argue is the most fundamental factorization in robotics: separating the world from the task. We investigate the conditions under which this factorization is principled. World factors are properties of the embodied system and the environment; they exist independently of intent. Task factors are defined by the task's logic over what the world admits. We formalize this asymmetry through Bayesian model...
论文介绍 本文探讨机器人学习中策略泛化到新约束、队友和环境的问题。提出世界-任务因子化作为基础分解方式，将策略结构化为世界因素（如系统和环境属性）和任务因素（如任务逻辑），并通过贝叶斯模型形式化这种不对称性，为机器人学习提供原则性框架以改善泛化和再训练效率。
第一作者: Shalfun Li · 方向: VLA 通用模型 · 来源: cs.RO
世界动作模型语义事件视觉-语言-动作预训练粒度对齐
Abstract:WALL-WM is a World Action Model that shifts video-action learning from chunk-centric optimization to event-grounded Vision-Language-Action pretraining, using semantically coherent action events as the atomic unit of learning. Existing WAMs commonly initialize from multimodal or video foundation models and then optimize fixed-length action chunks conditioned directly on the current observation and instruction. Although convenient, this chunk-centric formulation creates a fundamental granularity mismatch. Language describes semantic goals and events, vision evolves through continuous scene dynamics, and actions operate at control-level timescales; forcing all three into the same fixed-length prediction window turns VLA training into short-horizon correlation fitting. WALL-WM addresses this mismatch by organizing both supervision and data around semantic events. Specifically, it...
论文介绍 本文提出WALL-WM世界动作模型，将视频-动作学习从以固定长度动作块为中心转向以语义连贯事件为基础的视觉-语言-动作预训练。通过组织监督和数据围绕事件单元，解决语言、视觉和动作之间的时间尺度粒度不匹配问题，提升模型对语义目标和事件的理解与动作生成能力。
第一作者: Shoya Kuno · 方向: VLA 通用模型 · 来源: cs.RO
自我中心视频模仿学习导航任务联合训练数据增强
Abstract:Vision-language-action (VLA) models are promising for diverse robotic tasks, but their performance heavily depends on large-scale high-quality training data, whose collection on real robots is costly and time-consuming. While prior work has explored augmenting manipulation datasets with egocentric human videos, applying such approaches to mobile robot navigation remains challenging due to viewpoint changes during locomotion. In this paper, we propose a framework that converts egocentric walking videos into datasets for mobile robot imitation learning. The proposed method estimates camera motion from human videos and transforms it into action representations compatible with ground mobile robots. By jointly training a VLA model on human-derived and robot-collected datasets, the model achieves improved language understanding and more robust action generation than training with...
论文介绍 针对VLA模型在机器人导航任务中数据收集成本高的问题，本文提出将人类自我中心行走视频转换为移动机器人模仿学习数据集。通过从人类视频估计相机运动并转换为动作表示，与机器人收集数据进行联合训练，改善模型的语言理解能力和动作生成鲁棒性，降低对真实机器人数据的依赖。
第一作者: Zhaoting Li · 方向: 机器人操作 · 来源: cs.RO
扩散策略对比学习机器人操作行为克隆人机交互
Abstract:Diffusion policies have recently emerged as a powerful framework for robotic manipulation. However, like other behavior cloning methods, they remain vulnerable to distributional shift, often requiring human-in-the-loop interventions to correct failures during deployment. These interactions naturally provide paired supervision in the form of the robot's undesired actions and the human teacher's corrective actions. Yet existing data aggregation pipelines and standard behavior cloning losses largely ignore this negative signal from undesired actions, leading to overfitting to teacher's actions and an increasing reliance on costly expert data. To address this limitation, we propose Set-Supervised Diffusion Policy (SDP), a novel learning framework that utilizes contrastive action-chunk data to train diffusion policies from human corrections. From paired positive and negative...
论文介绍 该研究关注机器人操作中扩散策略面临的分布漂移问题，特别是人类修正反馈中未被充分利用的负样本信号。为解决此问题，论文提出了一种名为「集合监督扩散策略」的新学习框架。该框架利用从人类修正中构建的对比动作块数据，通过对比损失来训练扩散策略，旨在减少对专家数据的依赖并提升策略对分布漂移的鲁棒性。
第一作者: Kihyun Kim · 方向: 策略学习 · 来源: cs.RO
动作表征人形机器人策略学习周期性分解跨具身迁移
Abstract:Learning a good action embedding space is fundamental to scalable robot policy learning, yet existing methods treat action latents as task-specific intermediates rather than first-class representations. The resulting latents are unstructured, embodiment-specific, and weakly tied to motion semantics, limiting interpretability, controllability, and transferability across robots. We position the action embedding space itself as a first-class design target, with downstream policy quality emerging from representation quality. Exploiting motion's intrinsic periodicity, we factorize it into a phase manifold that captures cyclic structure via FFT-parametric coefficients, together with a pose branch that conditions the manifold on non-periodic configuration detail. Combined with motion-semantic distillation, this factorized structure yields a cross-embodiment motion manifold that is...
论文介绍 本研究指出当前机器人策略学习中的动作潜变量缺乏结构化，导致可解释性和跨机器人迁移能力不足。论文提出「PHASOR」框架，将动作嵌入空间本身作为核心设计目标。该方法利用运动固有的周期性，通过相位流形和姿态分支对动作进行分解，并结合运动语义蒸馏，旨在学习一个跨具身、结构化且与运动语义紧密关联的通用动作表征空间。
第一作者: Bing-Cheng Chuang · 方向: VLA 通用模型 · 来源: cs.RO
视觉-语言-动作模型SE(3)几何流形漂移坐标等变性扩散模型
Abstract:Diffusion-based Vision-Language-Action policies achieve remarkable success in robotic manipulation, yet commit a fundamental geometric error we term the $\textbf{Euclidean Fallacy}$: representing SE(3) poses as flat $\mathbb{R}^{12}$ vectors. This approximation induces (1) manifold drift violating SO(3) constraints, (2) broken equivariance under coordinate transformations, and (3) non-geodesic trajectories with excessive kinematic cost. We introduce $\textbf{Lie Diffuser Actor (LDA)}$, a diffusion framework operating intrinsically on SE(3). Our method injects noise through left-invariant SDEs, predicts scores in the tangent space, and retracts samples via the exponential map. This formulation eliminates manifold drift by construction while guaranteeing coordinate-frame equivariance and geodesic optimality. On CALVIN ABC$\rightarrow$D, LDA improves average task length from...
论文介绍 论文揭示了当前基于扩散的视觉-语言-动作策略在处理SE(3)位姿时存在的「欧几里得谬误」，即将其简化为扁平的R^12向量会导致流形漂移和非测地线轨迹。为此，作者提出了「李扩散器」框架，该框架内在地在SE(3)流形上进行操作，通过不变SDE注入噪声，在切空间预测得分并利用指数映射回撤样本，从而保证几何一致性、坐标系等变性和轨迹最优性。
第一作者: Yixuan Yang · 方向: 机器人操作 · 来源: cs.RO
透明物体体素占用估计机器人抓取单视图感知仿真到现实
Abstract:Transparent objects remain challenging for robotic perception due to unreliable depth sensing caused by refraction and reflection. While prior approaches rely on multi-view reconstruction or depth completion, they are often difficult to scale or deploy in real-world robotic systems. In this paper, we present a practical framework for transparent object perception and manipulation based on single-view RGB input. Our approach predicts voxel-space occupancy directly from a single image, providing a geometry-aware representation that supports downstream robotic grasping. To enable large-scale training, we construct a simulation pipeline that generates paired RGB images and voxel occupancy annotations under diverse materials and lighting conditions. We demonstrate that the predicted occupancy representation is robust to domain shifts and transfers effectively from simulation to...
论文介绍 透明物体的深度感知因折射和反射而不可靠，给机器人操作带来挑战。本文提出一种基于单视图RGB输入的实用框架「Trans2Occ」。该框架直接从单张图像预测体素空间的占用情况，为机器人抓取提供几何感知的表征。为了实现大规模训练，研究构建了仿真管线以生成多样化材料和光照条件下的配对数据。实验表明，该占用表征能有效从仿真迁移到现实。
第一作者: Axel Dawne · 方向: 具身智能 · 来源: cs.RO
抛掷翻转稳定抓取运动规划具身操作高自由度机械臂
Abstract:We propose FlipItRight, a framework for stable planar pose-targeted throw-flip with a high-DoF manipulator. The task is decomposed into an object-level planner, which generates candidate release states satisfying the desired landing pose, and a robot-level planner, which evaluates executability and constructs a feasible swing motion. Treating the release state as an explicit intermediate representation enables principled candidate filtering, adaptive selection of release and pre-swing configurations, and structured near-release motion design -- in particular, approximately constant end-effector velocities during the final swing phase to improve robustness to release-timing uncertainty. We validate on a real platform across objects of varying shape, size, and mass, achieving a 90% success rate across 120 trials. Ablation studies confirm that each design choice contributes to...
论文介绍 本研究针对机器人稳定抛掷并翻转物体至目标位姿的任务，提出了「FlipItRight」规划框架。该框架将任务分解为物体层规划器（生成满足目标落地位姿的释放状态候选）和机器人层规划器（评估可执行性并构建可行的摆动动作）。通过将释放状态作为显式中间表示，实现了候选筛选、自适应配置选择和鲁棒的释放前运动设计，从而提升了对释放时机不确定性的容忍度。
第一作者: Zixuan Jin · 方向: 具身智能 · 来源: cs.RO
机器人群体涌现行为物理信息建模多阶段演化密度场
Abstract:Robot swarms can exhibit coherent collective behaviors through local perception, limited communication and decentralized decision-making, yet modeling and controlling such emergence remains challenging when behaviors unfold over multiple phases. Here we introduce PhySwarm, a physics-informed micro--macro framework that represents multi-stage swarm emergence as physically constrained density-field evolution coupled to executable robot motion. At the macroscopic level, a multi-phase advection--diffusion--reaction model (Macro-ADR) describes phase-dependent swarm-density evolution through directed transport, diffusion-based spatial regulation and behavioral phase transitions. At the microscopic level, an equivalent deterministic motion model (Micro-EDM) realizes these mechanisms through potential-field advection, density-gradient compensation and rate- or event-gated phase...
论文介绍 机器人群体中涌现行为的建模与控制极具挑战，尤其是在行为多阶段展开时。本文提出了「PhySwarm」物理信息微观-宏观框架。宏观上，多阶段平流-扩散-反应模型描述群体密度的演化；微观上，等价确定性运动模型通过势场、密度梯度补偿和相位门控机制来实现这些动态。该框架将多阶段群体涌现表征为物理约束下的密度场演化，并耦合至可执行的机器人运动。
第一作者: Ceng Zhang · 方向: 导航与运动 · 来源: cs.RO
3D场景图物体表征超二次曲面碰撞检测机器人导航
Abstract:Hierarchical 3D Scene Graphs (3DSG) have emerged as an actionable and scalable representation for long-term autonomy incorporating metric, semantic, and topological information in the scene. However, the question of geometric representation of objects in 3DSG has been overlooked as most methods use simplified geometric models such as partial point clouds or 3D bounding boxes. In this work, we introduce a hierarchical object representation that can be leveraged for high-fidelity object-level reconstruction, object-based robust re-localization or map alignment, and efficient and analytical collision checking for safe robot navigation planning in dense and cluttered environments. The representation is structurally organized into four distinct layers, progressively abstracting the scene from raw sensor data to dense 3D meshes to analytical primitives such as superquadrics, which...
论文介绍 在分层3D场景图中，物体的几何表征常被简化，限制了其在精细任务中的应用。本工作引入一种分层物体表征，包含从原始传感器数据到密集网格再到超二次曲面等解析基元的四个层级。这种表征支持高保真物体重建、基于物体的稳健重定位或地图对齐，以及为密集杂乱环境中的安全机器人导航规划提供高效、解析的碰撞检测。
第一作者: Hao Liu · 方向: 具身智能 · 来源: cs.RO
多机器人网络通信连通性控制屏障函数预设时间控制重连触发
Abstract:In multi-robot systems, maintaining persistent communication graph connectivity is often overly restrictive, especially when robots have limited communication ranges but operate in large environments. Instead, allowing robots to temporarily disconnect and later reconnect is often more desirable for efficient task execution while still ensuring timely information sharing across the team. In this paper, we propose an adaptive prescribed-time control barrier function (adaptive PT-CBF) framework that enables robots to temporarily disconnect and re-enter the communication range within an adjustable and feasible prescribed time. Moreover, we introduce a reconnection triggering mechanism that jointly considers task execution and reconnection urgency, thereby providing a principled way to decide when reconnection should occur. Theoretical analysis justifies convergence to the...
论文介绍 多机器人系统中，持续保持通信图连通性过于严格。本文提出一种自适应预设时间控制屏障函数框架，允许机器人临时断开连接，并在可调整且可行的预设时间内重新进入通信范围。此外，论文引入了一个重连触发机制，该机制联合考虑任务执行和重连紧迫性，为决定何时应进行重连提供了一个有原则的方法。理论分析证明了收敛性。
第一作者: Martin Schuck · 方向: 策略学习 · 来源: cs.RO
无人机模拟器GPU 加速可微分多智能体策略学习
Abstract:High-quality, large-scale synthetic data from simulations is becoming a cornerstone for pushing the capabilities of robot algorithms. While aerial robotics simulators have evolved to support specialized needs such as fidelity, differentiability, and swarms independently, a unified platform that can synthesize data across all these domains is missing. In this work, we propose Crazyflow, a simulator designed to push the limits of aerial-robotics algorithm development, from model-based to data-driven methods, gradient-based to sampling-based approaches, and single-agent to multi-agent systems. Compared to existing state-of-the-art drone simulators, it achieves speeds more than an order of magnitude faster for a single drone and can simulate thousands of swarms of 4000 drones each. Real-world experiments show Crazyflow supports both analytical-gradient-based policy learning...
论文介绍 现有无人机模拟器在保真度、可微性与集群支持上各自为战，缺乏统一平台。本文提出 Crazyflow，一个基于 JAX 实现的高保真、可微分无人机模拟器。其核心优势在于极快的仿真速度（单机快一个数量级）和大规模集群支持（可模拟数千架），同时支持分析梯度与采样类策略学习方法。该平台有望成为推动从模型驱动到数据驱动的各类空中机器人算法开发的强大工具。
第一作者: Hojune Kim · 方向: VLA 通用模型 · 来源: cs.RO
人形机器人操作运动视觉语言动作模型高斯喷溅免遥操作
Abstract:Training vision-language-action (VLA) policies for humanoid loco-manipulation is constrained by the high cost and complexity of collecting human teleoperation demonstrations. VLA policies fine-tuned in simulators have, until now, failed to transfer effectively in humanoid loco-manipulation tasks. We present LEGS (Loco-manipulation via Embodied Gaussian Splatting), a hybrid simulator that composites a mesh foreground (robot, objects, props) over a photorealistic 3D Gaussian Splatting (3DGS) background reconstructed from a handheld scene capture. LEGS uses a procedural motion-primitive generator to synthesize labeled demonstrations at scale without human teleoperation, and a deterministic two-stage color calibration to align the rendered 3DGS image to the robot's deployment camera. On a Unitree G1 humanoid robot, across three pick-and-place tasks of increasing whole-body...
论文介绍 训练用于人形机器人操作运动的视觉语言动作策略成本高昂，且模拟器训练的策略难以迁移。本文提出 LEGS 混合模拟器，它将网格化的前景（机器人、物体）与基于手持扫描重建的高斯喷溅逼真背景相结合。核心创新在于使用程序化运动生成器自动合成大量带标签的演示数据，无需人工遥操作，并通过颜色校准确保视觉真实性。在真实人形机器人上的实验表明了该方法在抓取放置任务中的有效性。
第一作者: Weitung Chen · 方向: 数据集与评测 · 来源: cs.RO
水下感知跨模态声纳视觉数据集鱼群检测
Abstract:Underwater robots typically use both cameras and sonar for perception to leverage the rich semantic details of vision and the robust range measurements of acoustics. However, learning to map between these modalities via cross-modal prediction remains underexplored due to limited sonar-visual paired datasets. We present SOVIS, a sonar-visual dataset for cross-modal underwater perception. SOVIS comprises over 76,000 paired frames collected across 17 dives at six sites in the Trondheimfjord, supported by an end-to-end pipeline that cleans and synchronizes the cross-modal sensor data. We also introduce an interactive annotation tool designed to accelerate the labeling process for this paired data. Finally, we demonstrate a proof-of-concept cross-modal fish detection task using a small subset of labeled data, achieving a 7x improvement in mAP@0.10 over a monocular camera baseline...
论文介绍 水下机器人依赖摄像头和声纳感知，但配对数据稀缺阻碍了跨模态学习研究。本文提出了 SOVIS 数据集，包含超过 7.6 万帧来自 17 次潜水的声纳-视觉配对数据，并提供了数据清洗同步流程和交互式标注工具。作者通过一个概念验证的跨模态鱼类检测任务展示了数据集价值，基于少量标注数据训练的跨模态模型，其检测精度显著优于单目视觉基线。
第一作者: Guo Pu · 方向: 导航与运动 · 来源: cs.RO
主动重建单目视觉多视角立体轨迹规划机器人/无人机
Abstract:Active scene reconstruction enables robots/UAVs to autonomously plan trajectories and reconstruct environments without costly manual data acquisition. Unlike passive methods, active reconstruction requires real-time construction of high-confidence occupancy maps for collision-free navigation. Existing approaches rely on depth sensors for occupancy map updates, increasing platform cost and weight. To advance spatial intelligence, we aim for a vision-only monocular solution. However, current monocular scene reconstruction methods operate offline and fail to deliver globally consistent dense depth at the frame rates required for robots/UAVs navigation. To bridge this gap, we introduce ActMVS, the first framework for monocular active reconstruction. Our framework integrates a view factor graph construction for informed Multi-View Stereo depth prediction, along with a global depth...
论文介绍 主动场景重建要求机器人实时构建环境模型以规划无碰轨迹，现有方法多依赖深度传感器。本文旨在实现纯视觉的单目主动重建方案。针对当前单目方法无法实时提供全局一致深度的问题，提出了 ActMVS 框架。它通过构建视图因子图来指导多视角立体深度预测，并结合全局深度优化，为机器人导航提供了必要的实时占用图更新能力，从而推动基于视觉的空间智能发展。
第一作者: Zong Chen · 方向: 机器人操作 · 来源: cs.RO
轮腿机器人动态操作多物体运输深度集强化学习
Abstract:We study the problem of scaling dynamic loco-manipulation from a single free-rolling sphere to multiple spheres transported simultaneously on the back of a wheel-legged quadruped, without fences, grippers, or mechanical stops. Multiple identical free-rolling spheres form an unordered set with no persistent identity: their ordering may change independently at each history frame, creating a \emph{per-frame permutation symmetry} that standard history-concatenation set encoders do not explicitly enforce -- these encoders impose only a shared, diagonal permutation symmetry over the full history. We show that this symmetry mismatch leads to a concrete failure mode in curriculum-based reinforcement learning. Within the same PPO training budget, flat MLPs and branch-wise encoders plateau at or below the two-sphere stage, while a history-concatenation Deep Sets baseline (\HCDS) fails...
论文介绍 研究在轮腿机器人背上同时运输多个自由滚动球体的动态操作问题，无需夹具或围栏。核心挑战在于球体集合的无序性导致的「逐帧置换对称性」。研究发现，标准的基于历史的集合编码器因对称性不匹配而性能受限。本文提出 S2M-Trek，采用基于逐帧深度集的方法来显式处理此对称性。实验表明，该方法在强化学习训练预算内，相比基线能成功完成多球运输任务。
第一作者: Lingfeng Zhang · 方向: VLA 通用模型 · 来源: cs.RO
统一模型导航与操作视觉语言动作具身智能渐进式训练
Abstract:Navigation and manipulation are fundamental capabilities of embodied intelligence, enabling robots to interpret natural language commands and interact physically with their surroundings. However, current Vision-Language-Action (VLA) models remain constrained by task-specific architectures, specializing in either navigation or manipulation, which hinders the development of general-purpose robotic agents. To bridge this gap, we introduce OneVLA, a unified architecture that integrates these distinct tasks into a single, cohesive framework. Specifically, we design a unified action head capable of generating both navigation and manipulation actions without requiring task-specific variants. Furthermore, we propose a multi stage progressive training strategy-incorporating curated data construction and Chain-of-Thought (CoT) fine-tuning that facilitates strong positive transfer and...
论文介绍 当前视觉语言动作模型通常针对导航或操作任务专门设计，阻碍了通用智能体的发展。本文提出 OneVLA 统一框架，旨在将这两类任务整合到单一架构中。其核心是设计了一个能同时生成导航和操作动作的统一动作头，并辅以多阶段渐进式训练策略，包括数据构建和思维链微调。实验表明，该模型在多种导航和操作任务上展现出良好的性能与泛化能力。
第一作者: Raghav Mishra · 方向: 模仿学习 · 来源: cs.RO
模仿学习扩散策略闭式解免训练
Abstract:While diffusion-based policies have impressive performance and expressivity, their long offline training slows down the data collection and policy deployment loop. We introduce Closed-Form Diffusion Policies, a class of training-free diffusion-based policies for imitation learning using the closed-form score derived from the demonstration dataset. We deploy CFDP with real-time inference with a mobile CPU in hardware experiments, showing it can successfully perform imitation directly from the dataset in milliseconds and with faster inference than neural diffusion policies. In experiments on imitation learning benchmarks, we show that CFDP is competitive against neural baselines that require hours of training, providing a favorable tradeoff between training time and performance. Finally, we show how closed-form diffusion policies act as a composable primitive that enables...
论文介绍 基于扩散的策略性能强大，但训练耗时长。本文提出闭式扩散策略，它直接从演示数据集推导出闭式的得分函数，从而实现免训练的模仿学习。该方法在移动CPU上即可实现毫秒级实时推理，速度快于神经网络扩散策略。在基准测试中，其性能与需长时间训练的神经网络基线相当，在训练时间与性能间取得了良好权衡，并具备作为可组合原语的潜力。
第一作者: Xuchen Liu · 方向: VLA 通用模型 · 来源: cs.RO
视觉语言导航无人机世界模型扩散模型运动规划
Abstract:Vision-language navigation (VLN) for UAVs demands grounding free-form instructions into 6-DoF flight under partial observability. While Vision-Language-Action (VLA) models excel at semantic reasoning, they suffer from brittleness due to geometric inconsistency and dynamics mismatch. To address this, we propose ImagineUAV, an imagination-driven framework leveraging cascaded world-action modeling. Instead of direct regression, ImagineUAV employs a latent video diffusion model to generate instruction-conditioned future observations, explicitly imagining environmental evolution, from which 6-DoF motions are inferred via an action extractor. A kinodynamic planner then refines these estimates into collision-free trajectories. Additionally, a step-distilled inference pipeline ensures real-time execution. With only 1.3B parameters, ImagineUAV outperforms prior VLN and VLA baselines on...
论文介绍 无人机视觉语言导航需将自由语言指令转化为6自由度飞行，面临几何不一致和动力学失配的挑战。本文提出 ImagineUAV 框架，其核心是「想象驱动」的级联世界-动作建模。它不直接回归动作，而是利用潜在视频扩散模型根据指令生成未来的观测视频，显式想象环境变化，再从中推断动作。最后通过运动学动力学规划器优化出无碰轨迹，实现了仅13亿参数下优异的导航性能。
第一作者: Yang Gu · 方向: 具身智能 · 来源: cs.RO
异构海洋机器人动态避障缆绳安全感知无人水面艇混合遥控潜水器
Abstract:Heterogeneous marine robotic systems composed of an unmanned surface vehicle (USV) and a hybrid remotely operated vehicle (HROV) have shown great potential for subsea cable inspection. In such missions, the USV tracks the HROV at the surface while supplying power and communication through an umbilical tether. However, dynamic collision avoidance for the USV during HROV tracking is challenging because the submerged tether may scrape against passing vessels, while evasive maneuvers can enlarge the USV--HROV separation, thereby increasing the likelihood of tether tautness and compromising HROV operations. To address these challenges, this work proposes a tether-aware dynamic collision avoidance method for a USV tracking an HROV. First, a tether safety-aware planar domain is introduced to represent the three-dimensional collision risk between the tether and obstacle vessels...
论文介绍 本文研究了由无人水面艇（USV）和混合遥控潜水器（HROV）组成的异构海洋系统中的动态避障问题。由于USV通过缆绳为水下HROV供电和通信，其跟踪HROV时的避障需兼顾缆绳与过往船只的碰撞风险。为此，研究提出了一种缆绳感知的动态避障方法，通过引入缆绳安全感知的平面域来表征三维碰撞风险，旨在保障水下作业安全与系统稳定性。
第一作者: Zemin Yang · 方向: 导航与运动 · 来源: cs.RO
模仿学习行为克隆动作生成隐式策略条件专家几何
Abstract:Generative action policies based on diffusion or flow matching excel in behavior cloning, yet their iterative sampling is prohibitive for high-frequency robot control. While recent one-step formulations alleviate this latency, they inevitably discard the intermediate trajectory evolution that provides crucial action correction. Directly recovering this mechanism by explicitly estimating a training-time drifting field is mathematically ill-posed due to extreme conditional demonstration sparsity. We introduce Implicit Drifting Policy (IDP), a one-step imitation learning framework that brings the training-time correction of Drifting into policy learning without explicit vector field estimation. IDP extracts a conditional expert geometry from the local variation of observation-similar expert actions, and compares it against a global reference geometry to isolate condition-specific...
论文介绍 针对基于扩散或流匹配的生成式策略因迭代采样延迟而不适用于高频机器人控制的问题，本文提出了隐式漂移策略（IDP）。IDP是一种单步模仿学习框架，它通过从观测相似的专家动作局部变化中提取条件专家几何，隐式地将训练时的修正机制融入策略学习，避免了显式估计漂移向量场的不适定性问题，实现了高效的动作生成。
第一作者: Hung Mai · 方向: VLA 通用模型 · 来源: cs.RO
视觉语言动作模型世界动作模型机器人操作行为诊断表征分析
Abstract:Vision-language-action (VLA) policies and World-Action Models (WAM) represent two increasingly important paradigms for robotic manipulation. However, it remains unclear whether future prediction in WAMs leads to behaviorally meaningful improvements beyond final task success. In this paper, we ask whether WAMs merely add future prediction, or whether they change robot behavior and internal representations in ways that are actionable for control. We introduce a model-agnostic diagnostic framework that compares WAMs and VLAs through two complementary lenses: behavioral rollout analysis and sparse-autoencoder-based feature analysis. The behavioral protocol measures action dynamics consistency, target-object progress, distractor disturbance, and runtime cost. The feature-space protocol characterizes internal representations as memorized, reactive, or predictive, revealing whether...
论文介绍 本文关注视觉语言动作模型（VLA）和世界动作模型（WAM）在机器人操作中的作用。为评估WAM的未来预测是否带来超越任务成功率的行为改进，研究提出了一个模型无关的诊断框架。该框架通过行为轨迹分析和基于稀疏自编码器的特征分析，从动作一致性、目标进展、干扰项影响等角度，揭示两类模型在内部表征与机器人行为上的差异。
第一作者: Jianing Qian · 方向: 机器人操作 · 来源: cs.RO
模仿学习场景图部分可观测长时间推理移动操作
Abstract:Imitation learning enables robots to learn how to execute tasks via observation. However, real-world environments like homes and offices are often severely partially observed due to their large spatial scales. In addition, many tasks involve executing a series of subtasks requiring autonomous robots to reason over extended time horizons. To address these challenges, we propose using scene graphs as an explicit and structured memory mechanism in imitation learning. By maintaining a dynamic scene graph that captures object-centric relationships and their evolution over time, our method allows the agent to retain relevant historical context during task execution to efficiently reason over incrementally accrued scene information. Our experiments on simulated mobile manipulation and real-world tabletop manipulation demonstrate that our approach substantially improves policy...
论文介绍 为解决现实环境中因空间尺度大导致的部分可观测性以及长时间任务推理的挑战，本文提出在模仿学习中使用场景图作为显式的结构化记忆机制。通过维护一个动态场景图来捕捉以物体为中心的关系及其随时间的变化，该方法使智能体能在任务执行过程中保留相关历史上下文，从而更高效地对逐步积累的场景信息进行推理，提升策略性能。
第一作者: Zijia Chen · 方向: 机器人操作 · 来源: cs.RO
多模态学习混合专家模型机器人操作轨迹预测数据高效
Abstract:Robotic manipulation requires the effective integration of heterogeneous inputs, including visual observations, language instructions, and trajectory representations, to generate accurate actions. Existing transformer-based policies typically process these heterogeneous modalities within a shared parameter space, which often leads to modality interference and inefficient representation learning, especially in data-scarce scenarios. While Mixture-of-Experts (MoE) offers a scalable solution through expert specialization, conventional routing mechanisms are often sensitive to such cross-modal representation discrepancies, resulting in unstable expert assignment and expert collapse. In this work, we propose MATE (Multi-ModAl TrajEctory Policies), a novel trajectory prediction framework built upon MoE. Specifically, we introduce a Multi-Modal MoE architecture to achieve...
论文介绍 针对机器人操作中视觉、语言、轨迹等多模态输入的集成问题，现有基于Transformer的策略易因共享参数空间导致模态干扰，尤其在数据稀缺时效率低下。本文提出MATE，一个基于混合专家（MoE）的新型轨迹预测框架。它采用多模态MoE架构，通过设计专用的路由机制与专家结构，实现模态特异性处理与跨模态信息融合，以提高数据利用效率和动作预测的准确性。
第一作者: Ran Tian · 方向: 具身智能 · 来源: cs.RO
具身智能奖励模型机器人数据行为对齐负面数据
Abstract:This position paper argues that to obtain reliable embodied reward models, the community must invest in ``bad'' robot data: failed, suboptimal, error-prone, and even hazardous behaviors. While reward models are central to any foundation model's lifecycle, today's embodied reward models are trained primarily on successful behaviors. We analyze three state-of-the-art embodied reward models and find that they systematically over-reward behaviors that real human evaluators would penalize, including unsafe interactions, poor execution, and shortcut strategies that only superficially satisfy tasks. We attribute these failures to a key data gap: the scarcity of negative embodied data which is costly to collect and often filtered out or withheld in existing robotics datasets. Furthermore, we show that even modest exposure to real bad behavior data can improve alignment with human...
论文介绍 这篇立场论文主张，要获得可靠的具身奖励模型，必须投入建设包含失败、次优、错误甚至危险行为的「坏」机器人数据。研究分析了当前主流的具身奖励模型，发现它们主要基于成功行为训练，会系统性高估一些人类评估者会惩罚的行为。论文指出，现有机器人数据集中负面数据的稀缺是关键缺陷，并证明适度引入真实负面行为数据能显著提高模型与人类偏好的对齐程度。
第一作者: Pengfei Zhou · 方向: 机器人操作 · 来源: cs.RO
世界模型视频预测机器人操作策略学习动作评估
Abstract:Robotic manipulation requires models that generate executable actions while anticipating and evaluating their future consequences before physical execution. We present $\tau_0$-World Model ($\tau_0$-WM), a unified video-action world model that integrates policy learning, video prediction, and action evaluation within a single future-predictive framework. Built on a shared video diffusion backbone, $\tau_0$-WM provides two complementary interfaces. First, a video action model jointly predicts future visual latents and continuous action chunks from multi-view observations, language instructions, and robot state. Second, an action-conditioned video simulator rolls out candidate action chunks into multi-view futures and predicts dense task-progress scores. The model is trained on approximately $27{,}300$ hours of real-robot teleoperation, UMI-style interaction, egocentric human...
论文介绍 本文提出了τ₀-WM，一个统一的视频-动作世界模型，旨在将策略学习、视频预测和动作评估整合到单一的未来预测框架中。该模型基于共享的视频扩散骨干，提供两个接口：视频动作模型从多视角观测等输入联合预测未来视觉潜变量和动作序列；动作条件视频模拟器则将候选动作序列展开为多视角未来，并预测任务进展分数。
第一作者: Ranulfo Bezerra · 方向: 具身智能 · 来源: cs.RO
人工智能物联网机器人学系统集成小语言模型综述
Abstract:The convergence of Artificial Intelligence, the Internet of Things, and Robotics is no longer a futuristic vision; it is rapidly becoming the foundation of real-time, intelligent, and context-aware systems. AI enables perception and reasoning, IoT provides scalable sensing and communication, and robotics delivers embodied actuation. Despite significant progress in pairwise combinations such as AIoT and the Internet of Robotic Things (IoRT), there remains a lack of unified design frameworks that fully integrate all three. This survey synthesizes the state-of-the-art across these domains, emphasizing the emerging role of Small Language Models (SLMs) at the edge and Large Language Models (LLMs) in the cloud for distributed cognition and autonomous decision-making. We propose a modular system architecture that aligns with these trends, analyze persistent gaps in interoperability...
论文介绍 本综述探讨了人工智能、物联网与机器人学三者的融合趋势，强调了边缘端小语言模型（SLM）和云端大语言模型（LLM）在分布式认知与自主决策中的新兴作用。论文综合了各领域最新进展，提出了一种与这些趋势对齐的模块化系统架构，并分析了当前在互操作性、实时性及具身化等方面存在的差距，为构建互联的智能机器人系统指明路径。
第一作者: Beining Han · 方向: 机器人操作 · 来源: cs.RO
跨具身抓取6自由度抓取扩散模型夹爪表示扫掠体积启发式
Abstract:We study cross-embodiment 6-DOF robot grasping. Unlike prior works, we require the model not only to generalize to novel objects / scenes but also to novel gripper morphologies and physical grasping processes. Our method extends diffusion model based generative 6-DOF grasping models to condition on the additional gripper's representation. We propose a swept-volume heuristic for encoding the gripper. We train our cross-embodiment model with procedural grippers and a large-scale dataset of 2 Billion grasps. In simulation experiments, our model has the best zero-shot generalization to novel real-world grippers and objects over baseline methods. Our model also serves as a good initialization for fine-tuning to adapt to novel grippers. In ablations, we demonstrate the efficiency of our sweep-volume gripper representation and our procedural gripper training dataset. Last, we show...
论文介绍 本研究探讨跨具身6自由度机器人抓取问题，要求模型不仅泛化到新物体和场景，还能适应新夹爪形态和物理抓取过程。核心方法是将基于扩散模型的生成式6-DOF抓取模型扩展为条件化于夹爪表示，并提出扫掠体积启发式编码夹爪。通过程序化夹爪和大规模数据集训练，模型在模拟实验中展现出对新夹爪和物体的零样本泛化能力，并可作为微调的良好初始化。
第一作者: Hshmat Sahak · 方向: 导航与运动 · 来源: cs.RO
临时障碍物自适应导航生存曲线图规划清除时间分布
Abstract:A mobile robot following a graph of known routes can make costly navigation errors when a temporary obstacle blocks a critical edge: waiting too long behind a parked cart wastes time, but immediately rerouting around a person who would move in a few seconds is also inefficient. Standard reactive obstacle avoidance addresses local motion around obstacles, while fixed wait-or-reroute rules ignore how long different obstacle types tend to persist. We propose OSCAR: an adaptive survival-modeling framework for graph-based navigation with temporary blockages. Assuming obstacle class labels are available at encounter time, the robot learns class-conditioned residual clearance-time distributions from online experience, including right-censored observations when it reroutes before observing clearance. These survival models are integrated into a time-dependent graph planner that...
论文介绍 移动机器人在已知路线图上导航时，临时障碍物阻塞关键边会导致效率低下。现有方法缺乏对障碍物持续时间的考虑。本文提出OSCAR框架，一个自适应生存建模方法，用于处理图规划中的临时阻塞。通过在线经验学习障碍物类别条件的残余清除时间分布，并将其整合到时间依赖图规划器中，以优化等待或绕行决策，从而提高导航效率。
第一作者: Dan BW Choe · 方向: VLA 通用模型 · 来源: cs.RO
视觉-语言-动作模型长时程任务鲁棒性运动规划MPVI框架
Abstract:Vision-Language-Action (VLA) models have shown remarkable progress for mobile manipulation, but their performance on long-horizon tasks remains poor. These tasks are especially challenging because (1) progress toward high-level goals must be maintained across extended sequences of spatially distributed subtasks, and (2) early execution errors compound rapidly over the task horizon. These challenges persist despite finetuning on large human teleoperated mobile manipulation data, indicating that more data alone may not resolve the problem. To address these challenges, we propose MPVI: Motion Planner / VLA Interleaving, a framework that integrates model-based motion planning with VLAs to improve robustness without further training. The proposed integration enables localization and navigation to distant or occluded target objects through cluttered scenes using open-vocabulary...
论文介绍 视觉-语言-动作模型在长时程移动操作任务上表现不佳，早期执行错误易累积。现有数据微调方法效果有限。本文提出MPVI框架，通过交错集成基于模型的运动规划与VLA模型，在无需进一步训练的情况下提升鲁棒性。该集成支持在杂乱场景中定位和导航到远距离或遮挡的目标物体，增强长时程任务的完成能力。
第一作者: Keith Truongcao · 方向: VLA 通用模型 · 来源: cs.RO
视觉-语言-动作模型推理优化线程优化实时动作分块算法农业机械臂
Abstract:Vision-Language Action (VLA) models continue to face challenges such as slow inference speed and difficulty performing fine-grained motion adjustments, limiting their widespread adoption in industry. While the Real-Time Action Chunking (RTAC) algorithm has been proposed to address these bottlenecks, bridging the gap between the algorithm provided in pseudocode to a stable, real-world deployment on a low-cost robotic arm remains a challenge. In this work, we present a complete system-level implementation of RTAC tailored for a low-cost robotic manipulation system. We advance beyond the original high-level pseudocode by optimizing the threading implementation for the policy inference and control pipeline, reducing end-to-end latency and improving responsiveness without modifying the underlying policy. We evaluate this system on tasks involving the manipulation of agricultural...
论文介绍 视觉-语言-动作模型推理速度慢，限制了其在低成本工业机器人中的应用。本文针对实时动作分块算法，提出一个系统级实现，优化策略推理和控制管线的线程，以减少端到端延迟并提高响应性。该优化无需修改底层策略，并在农业机械臂任务上进行评估，展示了其在低成本操作环境中的实用性。
第一作者: Suk Ki Lee · 方向: 导航与运动 · 来源: cs.RO
多机器人运动规划扩散模型多智能体强化学习轨迹生成协调规划
Abstract:Coordinating multiple robots in shared environments requires generating feasible trajectories for each agent while accounting for interactions among agents. Centralized planning approaches become difficult to scale as the number of robots increases, while decentralized approaches that allow each agent to plan independently do not inherently account for inter-agent interactions. This paper presents a framework for coordinated multi-robot motion planning that combines decentralized generative trajectory planning with multi-agent reinforcement learning (MARL)-based coordination. Each robot independently generates candidate trajectories using a diffusion model trained on single-agent motion data, leveraging the generative model's ability to produce feasible and diverse trajectories. To reduce conflicts between agents, a centralized value function trained via MARL guides the...
论文介绍 多机器人在共享环境中协调运动需要生成可行轨迹并处理交互。中心化方法可扩展性差，去中心化方法缺乏交互考虑。本文提出一个框架，结合去中心化生成轨迹规划与多智能体强化学习指导。每个机器人使用扩散模型独立生成候选轨迹，集中式价值函数通过MARL训练来减少冲突，从而提升协调效率。
第一作者: Jialiang Fan · 方向: VLA 通用模型 · 来源: cs.RO
视觉-语言-动作模型安全评估基准测试信号时序逻辑成功率-安全差距
Abstract:Vision-language-action (VLA) benchmarks measure whether a policy completes a requested manipulation task, but binary success can hide safety-relevant trajectory behavior: reaching the goal while applying excessive contact, disturbing bystander objects, destabilizing the held object, or entering robot self-contact. We present SafeVLA-Bench, a post-hoc safety-evaluation framework for existing simulator-based VLA benchmarks. It formalizes task-aware safety requirements as Signal Temporal Logic (STL) specifications and reports native success with two unsafe-success metrics: Succ-But-Unsafe (SBU), the fraction of rollouts that both succeed and violate safety, and Violation Severity Index (VSI), a bounded worst-violation depth score. We instantiate SafeVLA-Bench on LIBERO and RoboCasa-365, evaluating nine policy-benchmark entries across tabletop and kitchen manipulation tasks. High...
论文介绍 现有视觉-语言-动作基准只关注任务成功与否，忽略了安全相关轨迹行为。本文提出SafeVLA-Bench，一个后置安全评估框架，将任务感知安全要求形式化为信号时序逻辑规范，并引入成功但不安全指标和违规严重度指数。该框架在多个模拟基准上评估VLA模型，揭示安全风险，促进更安全的操作研究。
第一作者: Nikhil Sethi · 方向: 导航与运动 · 来源: cs.RO
语义目标搜索微飞行器杂乱环境视点规划主动感知
Abstract:Autonomous target search is crucial for deploying Micro Aerial Vehicles (MAVs) in emergency response and rescue missions. Existing approaches either focus on 2D semantic navigation in structured environments -- which is less effective in complex 3D settings, or on robotic exploration in cluttered spaces -- which often lacks the semantic reasoning needed for efficient target search. This paper overcomes these limitations by proposing a novel framework that utilizes a semantically-guided viewpoint planner to minimize target search and exploration time in unstructured 3D environments using an MAV. Specifically, we develop a combinatorial planner that generates efficient semantic exploration plans by prioritizing viewpoints that likely lead to the target. To guide the planner towards the target, an active perception pipeline is developed that propagates semantic priorities of...
论文介绍 自主目标搜索对微飞行器在应急响应任务中至关重要，但现有方法在复杂3D环境中效率不足。本文提出STEM框架，利用语义引导的视点规划器来最小化搜索和探索时间。通过组合规划生成高效语义探索计划，并结合主动感知管道传播语义优先级，以在杂乱环境中实现快速目标发现。
第一作者: Yuichiro Aoyama · 方向: 导航与运动 · 来源: cs.RO
非凸模型预测控制最大熵微分动态规划优化机制采样扰动梯度下降
Abstract:This paper investigates the optimization mechanisms of non-convex Model Predictive Control (MPC) using the Maximum Entropy Differential Dynamic Programming (ME-DDP) framework. Navigating non-convex cost landscapes induced by nonlinear dynamics, multiple obstacles, etc. remains a fundamental challenge in robotics, where gradient-based methods frequently converge to suboptimal local minima. We demonstrate a dual-step optimization mechanism designed to overcome these traps. (1) an initial phase of using DDP to exploit the gradient of the cost landscape, followed by (2) disruption of the optimization via sampling from policies characterized by the inverse Hessian of the action-value function. We provide a rigorous analysis of this sampling mechanism of three ME-DDP variants: Unimodal Gaussian ME-DDP, Multimodal Gaussian ME-DDP, and Stein Variational DDP. Furthermore, with...
论文介绍 非凸模型预测控制在机器人导航中面临梯度方法易陷入局部最优的挑战。本文研究基于最大熵微分动态编程的优化机制，提出双步优化：先利用梯度下降探索成本景观，再通过采样扰动打破局部陷阱。分析三种ME-DDP变体的采样机制，为处理非凸成本函数提供理论基础和实用方法。
第一作者: Roland Andrews · 方向: 模仿学习 · 来源: cs.RO
模仿学习不可行优化增广拉格朗日方法约束满足安全策略
Abstract:Imitation learning (IL) is an effective approach to train complex robotics policies. Recent works have introduced hard constraints into imitation-learning optimization problems to ensure safety, stability, and robustness of the learned policy. However, we argue that these constraints are sometimes infeasible, which can lead to unstable or difficult training dynamics. We study a simple remedy for such situations based on recent theoretical results on the augmented Lagrangian method in infeasible settings. We show that our approach drives the learned policy toward the solution of a closest-feasible constrained IL problem with desirable properties. The method is illustrated on a toy driving example with a total-acceleration constraint and pedestrian-safety constraints, a setting in which infeasibility can naturally arise while still allowing a safe learned policy.
论文介绍 本文研究模仿学习中引入硬约束导致的不可行优化问题，这些约束可能使训练不稳定。基于增广拉格朗日方法在不可行设置下的理论结果，提出一种补救方法，驱动学习策略趋向于最近可行的约束模仿学习问题解。该方法在具有总加速约束和行人安全约束的玩具驾驶示例中展示，适用于机器人安全策略学习。
第一作者: Mohit Singh · 方向: 导航与运动 · 来源: cs.RO
视觉惯性里程计鸟瞰视图稀疏更新月球导航特征匹配
Abstract:Visual-Inertial Odometry (VIO) provides smooth, high-rate state estimates and has been widely used for robotic navigation in both terrestrial and planetary applications. However, its performance is typically dependent on the frequency of visual updates, which is a challenge for planetary rovers operating under extreme resource constraints and low frame rates. This work investigates enabling reliable VIO with very sparse visual updates for lunar rover applications, addressing both day and night-time operations where feature associations become especially difficult under self-illumination conditions. We propose a Bird's Eye View (BEV)-based image matching scheme that remains robust to larger inter-frame motions and more reliable feature matching despite significant visual appearance changes. We extensively evaluate our proposed approach, BEVIO, through high-fidelity...
论文介绍 本文针对行星探测车在极端资源约束和低帧率下的导航挑战，提出BEVIO方法。该方法基于鸟瞰视图进行图像匹配，在稀疏视觉更新和自光照条件下保持鲁棒性，实现可靠的视觉惯性里程计，适用于月球日夜导航任务。
第一作者: Nico Bohlinger · 方向: 策略学习 · 来源: cs.RO
机器人设计多体学习值梯度强化学习体态优化
Abstract:We propose to turn generalist multi-embodiment value functions into reusable models for robot design. Instead of running a new reinforcement learning co-design loop for each robot, we first train an embodiment-aware policy and value function across many robot designs. After training, the frozen value function is used as a differentiable surrogate to optimize candidate embodiments through value gradients. We evaluate our approach across different robot design settings, from perturbed single robots to held-out robots across morphology classes, with single models trained on up to 50 robots and design spaces of over 1100 continuous embodiment parameters. Beyond optimizing complete embodiments, we show that value gradients can identify performance-limiting design and control parameters, enabling both the optimization and the analysis of new robot designs.
论文介绍 本文提出将多体值函数转化为机器人设计的可重用模型。通过训练跨多体的策略和值函数，冻结值函数后利用值梯度优化候选体态，该方法可优化完整体态并识别性能限制参数，适用于机器人设计与分析。
第一作者: Ziheng He · 方向: 机器人操作 · 来源: cs.RO
具身世界模型关键帧插值稀疏视频生成机器人操作任务事件
Abstract:Embodied world models have emerged as a promising paradigm in robotics by predicting how robot actions affect the surrounding scene. However, the rollout inference remains computationally expensive in pixel space, as long-horizon manipulation videos typically have to be generated frame by frame. This cost cannot be easily reduced by indiscriminately dropping frames, since downstream policies rely on complete preservation of sparse task-relevant events such as approach, contact, grasp, and release. To address this challenge, we propose Sparse Keyframe Interpolation Paradigm (SKIP), an event-preserving sparse-to-dense framework that avoids dense frame-by-frame generation. SKIP first identifies task-relevant keyframes by leveraging robot-aware multimodal features. It then synthesizes only these keyframes with a sparse video diffusion model. A learned gap predictor and an...
论文介绍 本文针对具身世界模型在像素空间长时程操作中计算昂贵的问题，提出稀疏关键帧插值范式SKIP。该框架通过识别任务相关关键帧并合成稀疏视频，使用间隙预测器插值中间帧，避免逐帧生成，提高效率，适用于机器人操作策略学习。
第一作者: Shengcheng Fu · 方向: 导航与运动 · 来源: cs.RO
人形机器人地形编码注意力机制强化学习运动规划
Abstract:Although reinforcement learning has significantly advanced humanoid locomotion, perceptive policies still struggle on sparse-foothold terrain and constrained environments. Success in these scenarios requires both broad terrain awareness and precise foothold selection, two perceptual roles that conventional encoders often entangle. To address this challenge, we propose Global-Local Attention Decomposition (GLAD) for terrain encoding in humanoid locomotion. Realized by a coarse-to-fine encoder over a robot-centric elevation map, GLAD explicitly separates these objectives: a global attention branch utilizes attention pooling to summarize the surrounding terrain context, while a state-conditioned local attention branch sparsifies and encodes precise foothold-relevant geometry. This explicit attention decomposition prevents the dilution of fine-grained spatial cues while reducing...
论文介绍 本文针对人形机器人在稀疏立足点地形上运动的感知问题，提出全局-局部注意力分解GLAD方法。通过在机器人中心高程图上使用粗到精编码器，分离全局地形上下文和精确立足点几何，改善运动策略，适用于非结构化环境行走。
第一作者: Zhijie Yan · 方向: 机器人操作 · 来源: cs.RO
移动操作场景表示语义记忆SLAM动态环境
Abstract:Reliable mobile manipulation in dynamic indoor environments requires a scene representation that remains geometrically consistent, semantically queryable, and computationally bounded as the environment changes. Existing systems often rely on pre-built maps, static-scene assumptions, or highly accurate camera poses, which can lead to stale or misaligned scene information when target objects are relocated or pose estimates are corrected. This paper presents DREAM, a real-robot mobile manipulation framework that integrates perception, memory, localization, navigation, and manipulation in previously unseen indoor environments without a pre-built map. DREAM constructs an online spatio-semantic voxel memory from RGB-D observations registered by a LiDAR-inertial-visual SLAM backend. It further introduces pose-graph-aware Redundancy-Aware Memory Pruning (RMP) to update historical...
论文介绍 本文提出DREAM框架，实现动态室内环境中的可靠移动操作。该框架通过RGB-D观测构建在线体素语义记忆，并使用SLAM后端进行混合定位，引入冗余感知记忆剪枝来更新历史信息，无需预建地图，适应环境变化。
第一作者: Junnan Nie · 方向: VLA 通用模型 · 来源: cs.RO
动作分块执行时域相位感知机器人策略测试时调整
Abstract:Recent vision-language-action and diffusion-based robot policies often use action chunking, where each policy query predicts a sequence of future actions and the robot executes an open-loop prefix before re-querying. While this interface improves local motion continuity, deployment still requires choosing the execution horizon: how much of each predicted chunk should be executed before acquiring a new observation. However, our experiments show that success is strongly task-dependent and non-monotonic with respect to the execution horizon, making a single constant horizon an unreliable deployment rule. We propose PACE (Phase-Aware Chunk Execution), a training-free test-time execution method that selects the execution horizon online from the predicted chunk itself. PACE exploits the phase-dependent kinematic structure of manipulation trajectories by identifying low-speed...
论文介绍 本文研究动作分块策略中执行时域的选择问题，发现其任务依赖且非单调。提出PACE方法，在测试时从预测块中在线选择执行时域，利用操作轨迹的相位感知运动结构，识别低速阶段进行调整，提高策略部署灵活性。
第一作者: Haofan Cao · 方向: VLA 通用模型 · 来源: cs.RO
视觉语言动作模型接触丰富操作无源性控制合规控制安全操作
Abstract:Contact-rich manipulation demands both high-level semantic reasoning and the safe regulation of high-frequency contact dynamics. While Vision-Language-Action (VLA) models provide unprecedented semantic generalization, their low-rate outputs lack the reliability required for direct plant authority in force-sensitive tasks. To bridge this semantic-to-control gap, we introduce PaCo-VLA, a passivity-shielded compliance prior that recasts the VLA interface. Rather than trusting VLAs with direct motor commands, PaCo-VLA treats network outputs as task-level compliance proposals: semantic bindings, task stages, and admittance schedules. A high-frequency, proposal-independent passivity shield governs these proposals through energy-tank accounting and boundary checks, preventing invalid, stale, or unverified model predictions from bypassing low-level contact physics. This decoupled...
论文介绍 本文针对视觉语言动作模型在力敏感任务中的可靠性问题，提出PaCo-VLA方法。该方法将VLA输出视为任务级合规提案，并通过无源性屏蔽进行能量管理，防止无效预测绕过底层接触物理，实现安全接触丰富操作。
第一作者: Danyal Saqib · 方向: 具身智能 · 来源: cs.RO
物理人机交互能量意识控制自适应PD控制器机器人安全力控制
Abstract:Compliant force or torque control are approaches often investigated to achieve safe physical human-robot interaction (pHRI). However, these approaches have limitations. Force control requires a robot to be equipped with external force sensors to track the amplitude and direction of applied forces. Torque control requires torque sensing or estimation in each joint. As this is not available on every robot, energy-based approaches offer a promising alternative. Such approaches aim to achieve safe pHRI by limiting the mechanical energy of the robot. Current schemes leveraging an energy-based approach tend to have a complex implementation, and some may require further stability verification. We hence propose an adaptive proportional-derivative (PD) controller that can limit a robot's energy under any given limit to achieve safe pHRI. The proposed controller can limit both the...
论文介绍 研究物理人机交互中的安全控制问题，现有力控制和扭矩控制方法存在局限。提出一种自适应比例-微分控制器，通过限制机器人机械能量来实现安全交互，无需外部力传感器或关节扭矩传感。该方法可能应用于各种机器人平台，简化安全控制实现。
第一作者: Zijian An · 方向: VLA 通用模型 · 来源: cs.RO
机器人抓取方向感知几何感知农业机器人RGB-D感知
Abstract:Orientation-aware manipulation is essential in post-harvest agricultural processing, where produce must be grasped and placed in consistent configurations. This paper presents ROG-Grasp, a geometry-based robotic grasping and placement framework that estimates the produce orientation from root surface geometry using RGB-D perception. A YOLO-based root detector and point cloud plane fitting are used to infer the root normal, enabling stable grasp pose generation and orientation-constrained Cartesian motion planning. Experiments on tomatoes and onions demonstrate high success rates and stable execution time in both isolated and cluttered scenarios. Compared with vision-language-action (VLA) policies, the proposed method achieves more reliable and accurate grasp completion with faster execution. These results highlight the effectiveness of geometry-driven perception for practical...
论文介绍 针对农业后处理中方向感知操作的需求，提出ROG-Grasp框架。该框架利用RGB-D感知和YOLO根检测器，从根表面几何估计方向，生成稳定抓取姿势并执行方向约束的运动规划。实验表明在番茄和洋葱上具有高成功率，相比视觉-语言-动作策略更可靠准确。
第一作者: Carolina Silva-Plata · 方向: 具身智能 · 来源: cs.RO
软机器人触觉交互情感分析艺术装置气动执行器
Abstract:Soft robotics is increasingly explored in artistic contexts, where tactile interaction provides audiences with embodied engagement beyond visual or auditory signals. This work presents an interactive installation that maps semantic emotion analysis of narrative text into variable stiffness of soft pneumatic modules. A natural language model identifies two dominant emotions from a predefined set of six, driving the inflation of seven hexagonally arranged soft actuators. The central actuator represents the primary emotion, while the surrounding ones express the secondary. We develop and mechanically characterize silicone actuators, called soft modules, featuring a thin membrane layer, demonstrating how this morphological control expands the achievable stiffness range while preserving simplicity and low-cost fabrication. A user study with ten participants further evaluates how...
论文介绍 探索软机器人在艺术领域的应用，创建一个交互式触觉故事讲述装置。通过自然语言模型分析叙事文本中的情感，映射到软气动模块的刚度变化。开发了硅胶执行器，并进行用户研究评估触觉体验，展示了软机器人在文化表达中的潜力。
第一作者: Magnus Malthe Sigsgaard Nielsen · 方向: 具身智能 · 来源: cs.RO
软外骨骼抓取辅助3D打印触觉传感模块化设计
Abstract:Soft wearable robotic systems have emerged as a promising solution for assisting individuals with reduced hand function. This paper presents SoFiE, a modular soft finger exoskeleton designed to assist index-finger flexion during grasping tasks. The proposed system is primarily fabricated using 3D-printed flexible materials, enabling a lightweight, low-profile, and modular design. Actuation is achieved through a tendon-driven mechanism powered by a compact DC motor, while passive extension is provided by a compliant conductive spring. This element, termed StretchSense, also functions as a proprioceptive sensor by exhibiting resistance changes under deformation. Furthermore, a novel tactile sensing approach, MagSense, is introduced, using a magnet and magnetometer pair embedded in a soft fingertip structure to estimate contact force and object compliance. The system is fully...
论文介绍 介绍SoFiE，一个模块化软手指外骨骼，用于辅助索指屈曲抓取任务。主要采用3D打印柔性材料制造，结合肌腱驱动和被动伸展机构。集成StretchSense和MagSense传感器，提供本体感觉和触觉反馈。系统轻便、低成本，可能用于康复和辅助抓取。
第一作者: Theo Guegan · 方向: 模仿学习 · 来源: cs.RO
行为克隆模型预测控制神经网络实时控制机器人操作
Abstract:While Model Predictive Control (MPC) provides strong stability and robustness, it imposes a significant computational burden on real-time systems. This paper investigates the application of Behavior Cloning to approximate MPC policies for the real-time control of a 3-degree-of-freedom robotic manipulator. We present a baseline controller combining Inverse Kinematics with MPC and evaluate neural network architectures, ranging from classical regression algorithms to deep learning models including Deep MLPs and RNNs, to derive computationally efficient surrogate policies. We analyze generalization capabilities, stability considerations, and the trade-offs inherent in different architectural choices. Our empirical study employs both online and offline evaluations to assess performance regarding accuracy, computational efficiency, and fidelity to the original MPC policy. Our...
论文介绍 研究用行为克隆近似模型预测控制策略，以解决MPC的高计算负担问题，应用于3自由度机械臂实时控制。比较多种神经网络架构，从经典回归到深度学习模型，评估其泛化能力、稳定性和计算效率。实验证明行为克隆能有效模仿MPC策略。
第一作者: Daniel Morton · 方向: 模仿学习 · 来源: cs.RO
人形机器人全身跟踪约束控制强化学习控制障碍函数
Abstract:Recent advances in reinforcement learning (RL) have demonstrated impressive whole-body agility for humanoid robots, yet ensuring safety and satisfying constraints -- particularly those specified after training -- remains a challenge. Towards this goal, we present ConstrainedMimic, a control framework that leverages whole-body kinematics and dynamics for real-time constraint enforcement within RL tracking policies. By integrating principles from operational space control and control barrier functions (CBFs), we enable the satisfaction of arbitrary runtime constraints on both the kinematic reference motion and the underlying dynamics. In whole-body motion-tracking and teleoperation experiments on a (simulated) Unitree G1 with a learned policy, we demonstrate collision avoidance (both with the robot body and external obstacles), joint limits, and center of mass stability...
论文介绍 针对人形机器人运动控制中的安全和约束问题，提出ConstrainedMimic框架。该框架结合操作空间控制和控制障碍函数，在强化学习跟踪策略中实现实时约束满足，如碰撞避免、关节限制和质心稳定。在模拟Unitree G1上进行了验证。
第一作者: Jenna Kline · 方向: 多模态具身 · 来源: cs.RO
无人机数据集标准化FAIR原则跨学科动物生态
Abstract:Animal ecology data collection using drones represents a substantial investment of time, expertise, and financial resources. Yet most existing datasets serve only a single research community, limiting interdisciplinary reuse. We propose a unified drone dataset standard, FAIR^2 Drones, that bridges ecology, robotics, and computer vision by building on existing FAIR and AI-ready data frameworks while adding essential platform metadata and annotation specifications. Our standard enables datasets to simultaneously support ecological analysis, robotics algorithm development, and computer vision benchmarking. We provide open-source validation tools, reference implementations, and multimodal extensions linking drone imagery with complementary sensors such as camera traps, GPS, and acoustics. By standardizing metadata across disciplines, this framework maximizes the scientific return...
论文介绍 提出FAIR² Drones标准，以解决无人机数据集跨学科复用的限制。该标准扩展FAIR和AI-ready框架，添加平台元数据和注释规范，支持生态分析、机器人算法开发和计算机视觉基准测试。提供开源工具，最大化数据集科学回报。
第一作者: Christoffer Heckman · 方向: 具身智能 · 来源: cs.RO
基础模型几何感知一致性机器人地图持久映射
Abstract:Persistent maps used by autonomous robots increasingly fuse a geometric perception stack whose assertions are well-characterized with a foundation-model channel that produces semantic claims without calibrated reliability about the same scene. Contemporary mapping systems integrate the two channels by treating the foundation-model channel as an additional voter into a per-element posterior, uncalibrated for its own per-class reliability and without machinery to flag when the two channels contradict each other at a given moment. We propose an update operator with two cooperating mechanisms: a per-class calibrated commit gate, and a per-event conflict-drop window that refuses to commit foundation-model claims contradicted by the geometric channel at the moment of the claim. We evaluate on KITTI-360 and ScanNet, with an oracle geometric channel (panoptic ground truth) and an...
论文介绍 探讨在持久机器人地图中，基础模型语义证据与几何感知之间的一致性问题。提出一个更新操作符，包括校准门和冲突窗口，以处理两者间的矛盾。在KITTI-360和ScanNet上评估，增强地图的可靠性。
第一作者: Oussama Zaim · 方向: 策略学习 · 来源: cs.RO
深度强化学习位姿控制双阿克曼机器人执行不确定性模拟到模拟到现实
Abstract:Robust deployment of deep reinforcement learning (DRL) policies on real robots remains challenging due to discrepancies between simulation and real-world dynamics. We address this issue in the context of maneuvering with double-Ackermann-steering mobile robots, which introduce additional constraints due to their non-holonomic nature. Building upon the DRL framework ManeuverNet, we extend its objective from position control to full pose control, resulting in a more challenging task. We further investigate the impact of actuation-related uncertainties on policy transfer. The use of simplified actuation models during training of the extended policy can lead to poor generalization, shown by a success rate drop from 100% in PyBullet to 25% in Gazebo under stricter evaluation conditions. To address this limitation, we adopt a sim-to-sim-to-real approach, where actuation effects...
论文介绍 本文研究深度强化学习策略在双阿克曼机器人部署中的挑战，由于模拟与现实动力学差异及执行不确定性。核心方法扩展ManuverNet框架实现全位姿控制，并采用sim-to-sim-to-real策略处理执行效应，以提高非完整约束机器人的控制鲁棒性。
第一作者: Pau Montagut Bofi · 方向: VLA 通用模型 · 来源: cs.RO
视觉-语言-动作模型组误差移动操作器自由度异质联合
Abstract:Fine-tuning Vision-Language-Action (VLA) models for mobile manipulators with heterogeneous joint spaces can produce a counterintuitive result: the checkpoint with the lowest aggregate MSE is not the one that performs best on the real robot. We argue this is a predictable consequence of collapsing heterogeneous joint groups (arm, gripper, head, wheeled base) into a single metric, where easy-to-predict joints can mask joints that still fail. We fine-tune SmolVLA (450M, action-expert only) on the 11-DoF Toyota HSR and compare it against $\pi_{0.5}$ (3.3B), a stronger pretrained baseline. Per-group analysis exposes two patterns: in SmolVLA, the mobile base converges slowest and limits overall performance. In expert-only fine-tuning of $\pi_{0.5}$ (training only the action head, backbone frozen), total MSE drops below the baseline but arm accuracy degrades. On 60 real-robot trials...
论文介绍 针对异质联合空间移动操作器微调视觉-语言-动作模型时总均方误差可能误导性能评估的问题。核心方法提出按组分析误差，比较SmolVLA和π0.5模型，揭示移动基座收敛最慢限制整体性能。这为改进复杂机器人系统的模型微调提供见解。
第一作者: Songyang Liu · 方向: VLA 通用模型 · 来源: cs.RO
人形机器人悬浮负载模仿学习强化学习视觉-语言-动作模型
Abstract:Manipulating suspended payloads with humanoid robots is challenging because the robot can only influence an underactuated, oscillatory load through whole-body motion and intermittent contact. Imitation learning provides safe initial behavior but does not directly optimize final placement, while reinforcement learning from scratch is unsafe and sample-inefficient on real humanoids. We present HOIST-Humanoid Optimized with Imitation and Sample-efficient Tuning for manipulating suspended loads. HOIST first finetunes a high-level vision-language-action (VLA) policy from virtual-reality (VR) teleoperation demonstrations and executes its commands through a whole-body controller. It then uses VLA rollouts and iterative batched RL to improve placement accuracy and stopping behavior. Experiments in simulation and on a real humanoid show that HOIST improves over imitation-only and...
论文介绍 研究人形机器人操作悬浮负载的挑战，因欠驱动和振荡特性。核心方法HOIST结合模仿学习和高效强化学习：先从VR演示微调视觉-语言-动作策略，再通过迭代强化学习优化放置精度和停止行为。可提升人形机器人在复杂操作任务中的性能。
第一作者: Yueh-Hua Wu · 方向: VLA 通用模型 · 来源: cs.RO
视觉-语言-动作模型连续推理控制粒度推理介质时间扩展控制
Abstract:Natural language is a powerful reasoning medium for language and vision-language models, but it is mismatched to the granularity of continuous control. Text and explicit subgoals operate at task-level granularity, whereas vision-language-action (VLA) policies must choose actions at a much finer temporal scale; a single reasoning step can therefore span many action chunks while remaining only weakly coupled to the action needed now. This suggests a different question for VLA: what should play the role of language? We argue that a useful VLA reasoning medium must be shareable across model instances, verifiable through downstream action improvement, and aligned with temporally extended control structure. Based on this view, we propose Continuous Reasoning for Vision-Language-Action. Our model first predicts continuous reasoning in the form of a structured set of continuous...
论文介绍 探讨自然语言在视觉-语言-动作模型中作为推理介质的不匹配问题，语言粒度与连续控制需求不协调。核心方法提出连续推理，用结构化连续表示替代语言，以共享、可验证且对齐时间扩展控制结构。旨在改进策略推理与动作对齐。
第一作者: Christina Kohler · 方向: 具身智能 · 来源: cs.RO
弹性执行器并联弹性执行器串联弹性执行器非线性传动自行车模拟器
Abstract:Designing robots for high-torque, high-fidelity haptic interaction is challenging. Parallel Elastic Actuators (PEAs) use elastic elements in parallel to smaller motors to complement torques, and Series Elastic Actuators (SEAs) use elastic elements in series to decouple motor impedance and improve force control. Recent work combines SEAs and PEAs to obtain both benefits but requires separate elastic elements or clutching. This paper presents the Series Parallel Integrated Nonlinear Elastic Actuator (SPINEA), which merges SEA and PEA such that a single elastic element takes on dual roles simultaneously, parallel and series. This is achieved by a nonlinear transmission in which the motor and load have misaligned rotation axes and are elastically connected. This geometry enables both high peak torque and precise torque tracking. We apply SPINEA to actuate lean of a haptic bicycle...
论文介绍 针对高扭矩、高保真触觉交互机器人的设计挑战。核心方法提出SPINEA执行器，整合并联和串联弹性执行器优点，通过非线性传动使用单个弹性元件同时实现平行和串联作用。应用于自行车模拟器的倾斜运动，展示高峰值扭矩和精确扭矩跟踪能力。
第一作者: Alexander Nicholas White · 方向: 机器人操作 · 来源: cs.RO
生物启发软体机器人介电弹性体执行器游泳机器人自主平台
Abstract:Increasing interest in deep-sea operations and resources motivates the development of ecologically sensitive but environmentally durable robots. Dielectric elastomer actuator artificial muscles are good candidates for powering such systems due to their pressure and temperature tolerance and soft makeup, but they are difficult to integrate with robotic systems. This work presents an autonomous robotic platform: the CORE, capable of driving six artificial muscles while sensing visual and spatial information. To validate the platform, we developed the Cuttlebot - a cuttlefish-inspired robot that swims in three dimensions using undulatory fin locomotion. The Cuttlebot has four primary artificial muscles in its fins in addition to a tentacle-inspired soft gripper. The robot was evaluated in a series of tethered and untethered swimming tests, demonstrating a top speed of 2.5...
论文介绍 为深海操作开发生态敏感且环境耐久的机器人。核心方法提出Cuttlebot平台，使用介电弹性体人工肌肉驱动，模仿乌贼进行三维波动鳍游泳。平台集成视觉和空间传感，评估显示在系留和自主游泳测试中实现特定速度。为生物启发水下机器人提供示范。
第一作者: Leon Pohl · 方向: 多模态具身 · 来源: cs.RO
机器人数据集ROS bag构建过程依赖图可重复生成
Abstract:Robotic systems generate large volumes of multimodal sensor data, but converting ROS bag recordings into machine learning datasets is often handled by ad hoc sequential scripts, creating engineering overhead and slow iteration cycles. We model dataset construction as an artifact-based build process over a dependency graph and implement this approach in Bagzel, an open-source Bazel extension for reproducible, incremental dataset generation (including nuScenes-format export). We compare Bagzel and Bagzel-xattr (server-side digest management) against a sequential rosbag2nuscenes baseline. Bagzel reduces runtime in all evaluated execution modes, with the largest gains in iterative workflows (up to 386.26x in warm builds and 7.21x in incremental builds on a 20.4 GB dataset). Across dataset sizes from 5.1 to 20.4 GB, Bagzel variants show markedly better scaling behavior than the...
论文介绍 解决将ROS bag记录转换为机器学习数据集时的低效和工程开销问题。核心方法将数据集构建建模为基于依赖图的制品构建过程，并实现Bagzel工具作为Bazel扩展。实验证明在迭代工作流中显著减少运行时间，支持可重复和增量数据集生成。
第一作者: Yusuke Sano · 方向: VLA 通用模型 · 来源: cs.RO
视觉-语言-动作模型指令完成切换控制边界感知校准
Abstract:Vision-language-action (VLA) agents can execute natural-language instructions, yet deployed systems still lack an operational interface: deciding when the instruction is complete. This gap is acute in short composites ("do A, then B"), where mistimed handoffs cascade into downstream failures. Completion is inherently closed-loop because switching is an intervention that changes the instruction context and thus future actions and observations. We study completion under a deployable low-calibration regime motivated by open-ended instruction spaces, enforcing no test-time relearning and a single globally calibrated switching rule selected once on development set and reused unchanged on test set. Under this constraint, collapsing asymmetric boundary evidence into a single scalar can be brittle under polarity shifts across tasks. We propose Completion at the Boundary (CaB), which...
论文介绍 研究视觉-语言-动作代理如何判断自然语言指令何时完成，尤其在短复合指令中切换时机。核心方法提出Completion at the Boundary，在有限校准下实现可部署切换控制，避免测试时重学习。旨在提高VLA系统在现实任务中的操作可靠性。
第一作者: Amar Halilovic · 方向: 导航与运动 · 来源: cs.RO
本体引导推理affordance解释机器人导航状态变化本体论
Abstract:This paper proposes ontology-guided reasoning for affordance-based explanations of robot navigation. In human environments, it is not sufficient for a robot to detect that its route is blocked. It must also reason about what nearby objects afford, which state changes are possible, and which of these changes would allow it to continue safely. We address this problem by representing nearby entities, their affordances, affordance states, and qualitative spatial relations in a local affordance ontology and by evaluating hypothetical object--affordance state changes as candidate explanation factors. This yields explanations that are not only semantically grounded but also actionable. We instantiate the approach in a lightweight benchmark centered on a robot librarian scenario and evaluate it on procedurally generated navigation cases. The results show that ontology-guided reasoning...
论文介绍 本文提出了一种基于本体引导推理的方法，用于机器人导航中基于功能的解释。在人类环境中，机器人需推理附近物体的功能和状态变化，以生成可行动的解释。方法通过构建本地功能本体，表示实体、功能、状态及空间关系，并评估假设状态变化作为解释因素，实验在机器人图书馆员场景基准上验证了其语义基础和可行动性。
第一作者: Fangyuan Wang · 方向: VLA 通用模型 · 来源: cs.RO
世界模型机器人操纵综述未来表示动作条件学习
Abstract:Robotic manipulation depends on the ability to anticipate how actions reshape objects, contacts, and scene geometry before execution. Learned world models provide this capability by predicting task-relevant future evolution under robot intervention, yet the term now spans latent dynamics models, action-conditioned video generators, three- and four-dimensional scene predictors, physics-informed simulators, and predictive modules inside vision-language-action systems. This breadth has fragmented the literature and obscured the design choices that matter for manipulation. We survey world models for robotic manipulation through three questions: what future representation is predicted, how prediction is connected to action, and when prediction is used in the robot-learning pipeline. We operationally define a world model as an action-conditioned predictive system and distinguish it...
论文介绍 本文综述了机器人操纵中的世界模型。世界模型通过预测任务相关的未来演化来支持操纵能力，但现有术语多样，包括隐式动态模型和视频生成器等。文章通过三个问题系统梳理：预测什么未来表示、预测如何连接到动作、预测何时用于学习管道，将世界模型定义为动作条件预测系统，为设计选择提供清晰框架。
第一作者: Barak Or · 方向: VLA 通用模型 · 来源: cs.RO
静默失败物理AI运行时动作授权安全验证综述
Abstract:Physical AI systems increasingly map multimodal observations, language instructions, and learned world representations into physically consequential actions. Robotics foundation models, vision-language-action models, and world-model-based autonomous systems can condition decisions that move vehicles, robots, drones, and industrial machines. This transition exposes a safety problem that is not fully captured by conventional AI content moderation or by classical robot safety alone: a black-box model may issue a physically consequential action while appearing confident, plausible, and semantically aligned. The resulting failure can be silent, arising from sensor drift, occlusion, state-estimation error, distribution shift, hallucinated affordances, or invalid physical assumptions before downstream hardware controllers detect a violation. Across embodied foundation models, world...
论文介绍 本文综述了物理AI系统中运行时动作授权的文献。物理AI系统依赖黑盒模型生成动作，但可能因传感器错误或分布偏移导致静默失败，即看似合理却物理后果严重的动作。文章讨论现有方法如何确保动作安全，超越传统AI内容审核和机器人安全，为自主系统安全提供新视角。
第一作者: Helong Huang · 方向: 具身智能 · 来源: cs.RO
逆运动学图扩散机器人运动学关节配置生成结构感知
Abstract:Inverse kinematics (IK) is a fundamental problem in robotics, requiring the generation of joint configurations that satisfy target end-effector poses. Existing approaches often struggle to generalize across diverse robot morphologies and to effectively model the multi-modal nature of IK, particularly in articulated systems with multiple kinematic branches. In this work, we propose GraphDiff-IK, a structure-aware graph diffusion framework for inverse kinematics. Specifically, we represent the robot as a kinematic graph constructed from the robot URDF, where nodes correspond to actuated joints and edges encode kinematic dependencies. Building upon this representation, we formulate IK as a conditional graph diffusion process that directly generates joint configurations on the robot graph. To better capture structural dependencies in articulated systems, we further introduce a...
论文介绍 本文提出GraphDiff-IK，一种用于全身逆运动学的结构感知图扩散框架。逆运动学需生成满足目标末端执行器位姿的关节配置，但现有方法在多样机器人形态上泛化困难。GraphDiff-IK将机器人表示为运动图，将IK建模为条件图扩散过程，直接生成关节配置，并通过图神经网络捕捉结构依赖，提高泛化能力。
第一作者: Kerim Turacan · 方向: 具身智能 · 来源: cs.RO
不确定性感知LiDAR语义分割自校准证据狄利克雷表示自动驾驶
Abstract:LiDAR semantic segmentation is a core perception capability for autonomous vehicles and mobile robots. However, safe operation also depends on knowing when predictions are unreliable. Existing approaches typically rely on softmax confidence, which is often miscalibrated and overconfident, while stronger uncertainty estimates from Monte Carlo dropout or ensembles are often computationally expensive for real-time use. To this end, we introduce a novel, architecture-agnostic uncertainty-aware Adapter Head. It decomposes the prediction into a Preference Head for class ranking and a Strength Head that refines uncertainty assessment, thereby enabling a principled construction of evidential Dirichlet representations. Building on this design, we propose our inverse-vacuity self-calibration objective (Invascal), which directly supervises the strength signal to produce reliable and...
论文介绍 本文提出Invascal方法，用于不确定性感知的LiDAR距离视图语义分割。LiDAR分割对自动驾驶至关重要，但需要知道预测何时不可靠。Invascal引入一个架构无关的适配器头，分解预测为类别排序和不确定性评估，构建证据狄利克雷表示，并通过逆空虚自校准目标直接监督不确定性，实现可靠且实时的不确定性估计。
第一作者: Zhiyuan Feng · 方向: VLA 通用模型 · 来源: cs.RO
人类视频视觉语言动作模型机器人操纵可扩展学习动作表示
Abstract:Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models. However, most existing approaches rely on large collections of robot demonstrations, which are costly to obtain and tightly coupled to specific embodiments. Human videos, by contrast, are abundant and capture rich interactions, providing diverse semantic and physical cues for real-world manipulation. Yet, embodiment differences and the frequent absence of task-aligned annotations make their direct use in VLA models challenging. This survey provides a unified view of how human videos are transformed into effective knowledge for VLA models. We categorize existing approaches into four classes based on the action-related information they derive: (i) latent action representations that encode inter-frame changes; (ii) predictive world models that...
论文介绍 本文综述了利用人类视频进行可扩展视觉语言动作学习的方法。VLA模型依赖机器人演示数据，但获取成本高。人类视频丰富且多样，但具身差异和缺乏标注使其直接使用困难。文章分类现有方法为基于动作相关信息的四类，如潜在动作表示和预测世界模型，为利用人类视频增强机器人操纵能力提供统一视角。
第一作者: Zeqin Liao · 方向: VLA 通用模型 · 来源: cs.RO
视觉语言动作模型测试引导增强数据合成失败暴露模型微调
Abstract:Vision-Language-Action (VLA) models follow a data-driven paradigm and are constrained by the coverage of training data, making them prone to failure on edge-case configurations after deployment. To mitigate such risks, it is essential to expose high-quality failure modes and convert the resulting failures into supervisory data for model enhancement. Existing studies largely stop at failure detection and lack a mechanism for leveraging discovered failures for model repair. We propose VLAMotor, the first analysis framework for VLA enhancement, which integrates distance-aware model testing for failure exposure and agent-based data synthesis for model finetunning. First, VLAMotor estimates input uncertainty based on the distance to training samples, and combines uncertainty ranking with redundancy elimination to build compact test sets that expose diverse failures. Then, VLAMotor...
论文介绍 本文提出VLAMotor，首个视觉语言动作模型增强的分析框架。VLA模型受训练数据限制，易在边缘案例失败。VLAMotor集成距离感知模型测试以暴露失败，然后通过基于代理的数据合成生成监督数据进行微调，构建紧凑测试集暴露多样失败并修复模型，提升部署后鲁棒性。
第一作者: Xiang Xu · 方向: 具身智能 · 来源: cs.RO
4D LiDAR场景合成不确定性感知扩散模型空间熵具身智能
Abstract:Constructing faithful 4D worlds from LiDAR-acquired sequences is crucial for embodied AI, yet current generative frameworks apply uniform modeling capacity across all spatial regions. This ignores that perceptual difficulty varies dramatically within a single scan: distant surfaces, occluded boundaries, and small-scale objects carry far higher uncertainty than well-observed structures. We present U4D, a new framework that explicitly leverages spatial uncertainty to guide LiDAR scene generation in a "hard-to-easy" schedule. U4D derives per-point uncertainty maps via Shannon Entropy from a pretrained segmentor, then applies an unconditional diffusion stage to synthesize high-entropy areas with precise geometry, followed by a conditional completion stage that fills in the remaining regions using these structures as priors. A MoST (Mixture of Spatio-Temporal) block further...
论文介绍 本文提出U4D框架，用于不确定性感知的4D LiDAR场景合成。构建真实4D世界对具身AI至关重要，但现有生成模型对所有空间区域均匀建模，忽略感知难度差异。U4D利用空间不确定性地图引导生成，先通过无条件扩散合成高不确定性区域，再条件完成剩余部分，实现高效且准确的场景合成。
第一作者: Muyi Bao · 方向: 导航与运动 · 来源: cs.RO
视觉语言导航像素定位导航策略机器人运动统一空间接口
Abstract:Vision-language models (VLMs) have become a common foundation for vision-and-language navigation in continuous environments (VLN-CE). Yet most VLM-based methods cast navigation as low-level action prediction, an interface that is ambiguous, tied to short-horizon motion primitives, and inefficient due to repeated VLM querying. We propose Goal2Pixel, a pure pixel-based paradigm that reformulates VLN-CE as navigable pixel grounding. Rather than predicting actions, Goal2Pixel uses the image plane as a unified spatial interface between VLM reasoning and robot motion: the model predicts a visible navigable pixel to the agent, which is back-projected into a 3D waypoint for forward navigation. For non-forward actions, we append auxiliary directive regions to the image plane, where the left/right/bottom regions are interpreted as turning left, turning right, and stopping, respectively...
论文介绍 该研究针对连续环境中视觉语言导航的效率问题，提出 Goal2Pixel 方法。它将导航任务重新定义为可导航像素定位，通过预测可见可导航像素并反投影为 3D 航点，利用图像平面作为空间接口，避免重复查询 VLM。这种方法可能提升机器人导航的准确性和实时性。
第一作者: Huiqiong Li · 方向: 机器人操作 · 来源: cs.RO
视频世界模型机器人操作可信度评估基准测试多维度评估
Abstract:Video world models are increasingly used in robotic manipulation, yet existing benchmarks mostly evaluate them under valid, feasible, and safe instructions. We introduce RoboTrustBench, a benchmark for evaluating the trustworthiness of video world models under four scenarios: Normal, Constraint-Sensitive, Counterfactual, and Adversarial. Built from real-world DROID episodes, RoboTrustBench contains 1,207 expert-validated instruction-image pairs and a six-dimensional evaluation protocol with 13 fine-grained criteria. Evaluating seven representative video world models with human and MLLM assessment, we find that current models often generate visually coherent videos, but struggle with constraint reasoning, counterfactual grounding, physical interaction, and unsafe-instruction suppression. These results show that visual quality and surface-level instruction following are...
论文介绍 该工作引入 RoboTrustBench 基准，用于评估视频世界模型在机器人操作中的可信度。它涵盖正常、约束敏感、反事实和对抗性四种场景，包含 1,207 个指令-图像对和六维评估协议。评估发现当前模型在约束推理和物理交互方面存在不足，有助于推动更可靠模型的发展。
第一作者: Lucas Haug · 方向: 具身智能 · 来源: cs.RO
多智能体系统行为树机器人协调任务切换VSSS
Abstract:The application of multi-agent systems in robotics is a very challenging field. Several competitions involving such systems are proposed to foster research and development of strategies and mechanisms using games as the underlying domain. Among them are the ones from the \textit{IEEE Very Small Soccer (VSSS)} category, which is the case study described in this paper. In VSSS, two teams of three robots each compete in a very dynamic environment of a soccer game. Thus, coordination of robots' behavior during the game is crucial to win it. In this paper, we present a Behavior-Tree-based approach to support multi-robot coordination within the VSSS team of the ThundeRatz robotics team from the Universidade de S$\tilde{a}$o Paulo. Moreover, a comparison between the proposed approach and the previous one, which was based on a Finite State Machine (FSM), was conducted using the...
论文介绍 该论文研究多机器人系统中的行为协调，特别是在 IEEE Very Small Soccer 比赛中。采用行为树方法支持多机器人协调，并与有限状态机进行比较。结果显示行为树在动态环境中能有效提升团队协作，为复杂多智能体任务提供参考。
第一作者: Thien Tran · 方向: 具身智能 · 来源: cs.RO
边缘计算QoS 感知任务放置多机器人系统闭环控制
Abstract:Multi-robot systems (MRS) increasingly offload compute-intensive perception tasks to edge nodes to meet strict time-sensitive Quality-of-Service (QoS) constraints. However, static task orchestration on a shared edge node can severely degrade QoS due to network latency, jitter, and edge-resource contention. We present a pilot edge-centric MRS testbed using Raspberry Pi nodes to evaluate a camera-to-manipulator pipeline under three modes: local execution, static offloading, and a QoS-aware Adaptive Task Placement (ATP) controller. ATP scores candidate placements using a multi-metric cost (normalized latency, CPU utilization, and switching overhead) over two-second control windows. The closed-loop visual servoing testbed is instrumented with sub-millisecond clock synchronization, network emulation, and detailed monitoring of multiple metrics across nodes to capture realistic...
论文介绍 针对多机器人系统中静态任务编排导致 QoS 下降的问题，本文提出 QoS 感知自适应任务放置控制器。基于边缘节点的测试床，控制器使用多指标成本评分在控制窗口内优化放置决策。实验验证了其在时间敏感任务中的有效性。
第一作者: Thien Tran · 方向: 数据集与评测 · 来源: cs.RO
机器人教育通信架构开源平台仿真到现实ROS
Abstract:The persistent challenge in scaling authentic manipulator education within university laboratories is a structural dichotomy: commercial digital twins are often cost-prohibitive and rigidly scripted, whereas open-source robotics middleware (ROS) imposes steep technical and syntax barriers for novices. To resolve this logistical and educational friction, this Work-in-Progress (WiP) paper proposes a scalable four-tier communication architecture tailored for sustainable robotic curricula. Rather than focusing on software application design, our study examines the underlying data exchange mechanisms required to bridge visual conceptual environments with physical robotic endpoints, utilizing the Graphical Open-Source Platform (GOSP) as a foundational instantiation. This WiP details the framework's technical integration of 3D visual armature modeling with a robust ROS middleware...
论文介绍 为解决机器人教育中可扩展性和成本障碍，本文提出四层通信架构，整合图形开源平台 GOSP。该架构支持从 3D 可视化环境到物理机器人的数据交换，降低技术门槛。工作进展显示其在可持续课程中的应用潜力。
第一作者: Junwon Seo · 方向: 数据集与评测 · 来源: cs.RO
视频世界模型策略评估扩散模型高影响结果噪声优化
Abstract:Video world models (WMs) have shown promise for policy evaluation and improvement by imagining realistic future observations conditioned on ego-robot actions. While WMs can model distributions over futures, policy evaluation and improvement typically rely on nominal imaginations, which can miss high-impact outcomes of robot actions unless prohibitively many samples are drawn. To enable robust policy evaluation and improvement over WM imaginations, we propose StressDream, which steers imaginations toward high-impact yet plausible outcomes specified at inference time by optimizing the initial noise of diffusion-based WMs. However, optimizing high-dimensional noise is challenging: the optimization must reason about nuanced, scene-dependent target events in generated videos while avoiding out-of-distribution (OOD) noise that yields implausible imaginations. We address this with...
论文介绍 该研究提出 StressDream 方法，增强视频世界模型在策略评估中的鲁棒性。通过优化扩散模型的初始噪声，引导想象向高影响但合理的结果，避免过度采样。这有助于更准确地评估和改进机器人策略，减少假阳性。
第一作者: Huaihai Lyu · 方向: 具身智能 · 来源: cs.RO
具身智能动作流形时空解耦一般协变泛化
Abstract:Achieving robust generalization from limited data is a central challenge in embodied intelligence. Prevailing methods fail by regressing absolute coordinates, which violates the principle of general covariance. Fundamentally, this conflates the intrinsic task geometry with rigid execution patterns, binding policies to specific motion styles and fixed speeds. To resolve this, we propose the Generalized Action Manifold (GAM) framework that enforces general covariance through structural disentanglement. Specifically, GAM realizes the manifold by enforcing invariance across two orthogonal dimensions: (1) Temporal Invariance, utilizing an Arc-Length Parameterizer to orthogonalize the spatial path geometry from temporal dynamics, ensuring robustness to velocity variations; (2) Geometric Invariance, where a Schema-Affine-Factorization mechanism maps trajectories to canonical ``world...
论文介绍 本文提出广义动作流形（GAM）框架，通过时空解耦实现一般协变，提升从有限数据的泛化能力。GAM 通过时间不变性和几何不变性，将轨迹映射到规范坐标，避免绑定到特定运动风格。这为机器人学习中的策略泛化提供了新思路。
第一作者: Christian Gumbsch · 方向: 策略学习 · 来源: cs.RO
强化学习奖励模型视觉语言模型测试时适应示例优化
Abstract:Reinforcement learning relies on accurate reward functions, which are often hand-crafted or even unavailable in real-world applications, such as robotics. Recent work has explored the zero-shot reasoning capabilities of pre-trained Vision-Language Models (VLMs) as reward models. However, without careful prompt engineering, these approaches tend to produce suboptimal rewards, where false positive predictions can severely degrade downstream policy learning. In robotics, limited datasets comprising expert demonstrations are often collected to bootstrap policy learning. This scenario provides an opportunity to optimize a reward model prior policy training. We propose Demo2Reward a test-time adaptation technique to optimize the language instruction of a reward model based on a few demonstrations (3-10 trajectories) to reduce false positives while preserving true positives...
论文介绍 针对视觉语言模型作为奖励模型时提示工程不佳的问题，本文提出 Demo2Reward 测试时适应技术。基于少量示例优化语言指令，以减少假阳性并保留真阳性。这提升了奖励模型的准确性，有助于强化学习在机器人中的应用。
第一作者: Zhenyu Li · 方向: 导航与运动 · 来源: cs.CV
对抗攻击机器人定位深度学习产品量化特征扰动
Abstract:Robot localization systems are critical for autonomous navigation and safety. Adversarial perturbations can mislead these systems, resulting in mislocalization, navigation errors, or unsafe interactions, especially in mission-critical scenarios. This paper investigates the vulnerability of deep learning based localization pipelines to adversarial attacks. We propose a novel framework for generating adversarial queries that specifically target Product Quantization (PQ) in visual localization systems. Our method employs a Lightweight Product Quantization Network (LPQN) to perturb query feature encodings, misleading the retrieval process by returning semantically irrelevant database entries. Adversarial queries are generated via a two-phase procedure: a forward pass that perturbs feature distributions and a backward pass that refines the perturbation through optimization. The...
论文介绍 本文研究了基于深度学习的机器人定位系统对对抗攻击的脆弱性，提出了一种新框架生成针对视觉定位中产品量化的对抗查询。方法使用轻量级产品量化网络扰动查询特征编码，通过两阶段过程（前向传播扰动特征分布和后向传播优化细化）生成对抗查询，以误导检索过程返回语义无关条目。该研究有助于提升定位系统安全性，防止在任务关键场景中发生定位错误或导航失败。
第一作者: Stephen James Krol · 方向: 多模态具身 · 来源: cs.CV
进化系统美学评估视觉-语言模型CLIP-IQAGlicko评级系统
Abstract:Evolutionary systems have demonstrated remarkable results in creative domains, with recent applications in generative typography, design, and music. However, an open problem remains in designing fitness functions that effectively capture the desired aesthetics of abstract outputs. In this work, we explore two methods for evaluating the aesthetics of a population using Vision-Language Models (VLMs). The first method uses CLIP-IQA to predict an aesthetic score for each design. The second method instead pits candidates against each other, with winners determined by a VLM using a custom prompt specified by the user. The outcomes of these pairwise comparisons are then used to estimate a population ranking via the Glicko rating system. We present these methods in the context of a case study using a custom generative system and compare the resulting rankings with an artist's...
论文介绍 本文针对进化系统中设计适应度函数以评估抽象输出美学的难题，探索了两种利用视觉-语言模型的方法：一种使用CLIP-IQA预测美学分数，另一种通过VLM进行成对比较并用Glicko系统估计种群排名。这些方法在定制生成系统案例中展示了可行性，为创意设计领域的自动化美学评估提供了新思路。
第一作者: Wyame Benslimane · 方向: 策略学习 · 来源: cs.LG
决策聚焦学习上下文线性优化部分反馈在线策略学习梯度估计
Abstract:Decision-focused learning (DFL) trains predictive models by optimizing downstream decision quality rather than standalone prediction accuracy. For contextual linear optimization, most existing DFL methods assume offline data and full observations of the objective cost vector. We develop an on-policy learning method for sequential contextual linear optimization under partial feedback, generalizing the standard bandit feedback setting. Our method learns a stochastic predict-then-optimize policy that samples a cost-vector prediction from a conditional distribution and solves the resulting downstream linear optimization problem. To update this distributional model, we introduce a two-component hybrid gradient estimator. The first component is a score function estimator, which provides an unbiased but potentially high-variance policy gradient estimate. The second is a...
论文介绍 本文提出了一种在部分反馈下进行顺序上下文线性优化的在线策略学习方法，推广了标准bandit反馈设置。通过决策聚焦学习框架，模型学习随机预测-然后-优化策略，并采用混合梯度估计器（包括无偏分数函数估计器）更新条件分布，以优化下游决策质量，适用于资源分配等实际应用。
第一作者: Shao-An Yin · 方向: 具身智能 · 来源: cs.LG
广义纳什均衡问题分布式算法多机器人协调隐私保护连续时间系统
Abstract:Recent advances in artificial intelligence have expanded the focus from classical optimization to include equilibrium analysis in noncooperative games. Many such games involve shared constraints, leading to Generalized Nash Equilibrium Problems (GNEPs). Existing distributed algorithms typically require agents to exchange Lagrange multipliers to enforce consensus and compute variational-GNEs (v-GNEs). This work introduces fully distributed continuous-time algorithms and establishes convergence without requiring multiplier exchange, thereby reducing information exchange per iteration while improving privacy preservation. The analysis focuses on strongly monotone games with convex individual constraints and linear shared constraints. I also propose several discretization schemes for the continuous-time algorithms. The proposed approach converges to general GNEs, rather than being...
论文介绍 本文针对广义纳什均衡问题，提出了完全分布式连续时间算法，无需代理交换拉格朗日乘子，从而减少信息交换并增强隐私保护。算法在强单调博弈中收敛到一般GNE，并提供了离散化方案，可应用于多机器人协调和上下文bandit主动学习等场景，提升了分布式系统的实用性和安全性。
第一作者: Renhao Zhang · 方向: 策略学习 · 来源: cs.LG
扩散策略行为流形参数化控制策略学习机器人控制
Abstract:We propose Parameterized Diffusion Policy (PDP), a framework for learning diffusion policies conditioned on low-dimensional, continuous parameters embedded in a learned behavior manifold. By constructing this manifold so that distances between latent representations reflect the semantic similarity between physical trajectories, we transform diffusion from a mechanism for stochastic diversity into a precise and optimizable tool for behavior steering. Our approach enables smooth interpolation between known strategies and efficient adaptation to novel constraints without updating policy weights. We demonstrate that PDP significantly improves adaptation performance on complex multimodal benchmarks in both simulated and real-robot experiments compared to standard diffusion policies, particularly in scenarios requiring the synthesis of novel behaviors.
论文介绍 本文提出参数化扩散策略框架，通过学习的行为流形嵌入低维连续参数，将扩散机制从随机多样性工具转变为精确的行为转向工具。该方法实现已知策略间平滑插值和高效适应新约束，无需更新策略权重，在模拟和真实机器人实验中显著提升适应性能，尤其适用于合成新行为的复杂场景。
第一作者: Abhijith Babu · 方向: VLA 通用模型 · 来源: cs.AI
视觉-语言-动作模型闭环控制神经激活干预自适应控制具身智能
Abstract:Vision-Language-Action (VLA) models can be steered at test time by intervening on semantically meaningful internal directions, but existing methods use a fixed steering coefficient, effectively operating in open loop. This is poorly suited to embodied control, where task state and concept error evolve over time, often causing overcorrection, oscillation, and reduced task success, especially for temporal behaviors such as speed and smoothness. We propose CTRL-STEER, a closed-loop framework that replaces static intervention strength with adaptive, time-varying control signals. The key idea is to decouple representation from regulation: rather than assuming temporal concepts are directly controlled by individual neurons, we steer along motion-aligned residual directions while a feedback controller adjusts intervention magnitude online. We instantiate this framework with both PID...
论文介绍 本文指出视觉-语言-动作模型中开环干预的局限性，如过度校正和振荡，提出CTRL-STEER闭环框架。该框架使用自适应时变控制信号沿运动对齐残差方向进行神经激活干预，并通过反馈控制器在线调整干预幅度，解耦表示与调节，以提升具身控制任务成功率，特别是时间行为如速度和平滑度。
第一作者: Aritra Roy · 方向: 多模态具身 · 来源: cs.AI
材料数据提取科学图形视觉-语言模型多代理系统成分-性质数据库
Abstract:Automated extraction of materials composition-property data from scientific literature has advanced considerably with the development of large language model-based pipelines; however, existing frameworks remain limited to textual and tabular content, overlooking the substantial proportion of quantitative property data reported exclusively in scientific figures. Here, we extend ComProScanner, a fully end-to-end multi-agent framework for automated composition-property database construction, with a native vision-language model (VLM) based figure extraction capability. The extension introduces a FigureExtractor utility for caption-keyword-based figure filtering across all supported publishers, and a GraphExtractorTool agent that passes extracted figures to a configurable VLM to recover composition-property pairs from scientific charts and plots. Four VLMs are selected for...
论文介绍 本文扩展了ComProScanner多代理框架，集成原生视觉-语言模型以从科学图形中提取材料成分-性质数据。通过FigureExtractor实用程序和GraphExtractorTool代理，实现基于标题-关键词的图形过滤和VLM驱动的数据恢复，弥补现有方法忽略图形数据的缺陷，提高自动化材料数据库构建的准确性和完整性。
美股技术面整体偏强，SPY 和 QQQ 呈多头排列，RSI 分别处于 75.6 和 79.4 的超买区域，MACD 有金叉支持，但超买状态提示短期调整风险。加密市场极度疲软，恐慌贪婪指数仅为 11（极度恐慌），总市值 2.39 万亿美元 24 小时下跌 4.37%，BTC 主导率 56%，ETH 占 9.4%。主要加密货币如 BTC-USD、ETH-USD 和 SOL-USD 的 RSI 均低于 30，进入超卖区域，价格远低于移动平均线，空头排列明显，技术面持续下行。中概股表现分化，腾讯控股（0700.HK）MACD 金叉且近五日大涨 15.01%，而阿里巴巴（BABA）和拼多多（PDD）仍处空头排列，京东（JD）趋势中性。商品外汇方面，黄金期货（GC=F）价格 4500.7 中性震荡，RSI 43；原油期货（CL=F）价格 95.01 近五日涨 7.14%，但 RSI 48.5 未显强势；美元/人民币（USDCNY=X） RSI 29.3 超卖且空头排列，美元指数 DXY 则呈多头排列。整体市场技术信号混合，需关注超买超卖区域的动量变化。
RSI 为 79.4，处于超买区域；MACD 指标显示金叉，DIF 线 21.98 高于信号线 21.60；价格 746.16 位于 SMA20（716.13）、SMA50（659.21）和 SMA200（619.49）之上，呈现多头排列。近一日涨幅 0.46%，近五日涨幅 2.17%，技术动能强劲。
RSI 为 22.1，进入超卖区域；价格 66928.22 远低于 SMA20（75673.22）、SMA50（77091.45）和 SMA200（79243.35），形成空头排列；MACD 值为 -1857.69，信号线 -962.39，柱状图为负，确认下行趋势。近一日跌幅 6.16%，技术面疲软。
MACD 指标出现金叉，DIF 线 -6.49 高于信号线 -12.52；RSI 为 63.4，未进入超买；价格 499.6 在近一日上涨 3.74%，近五日大涨 15.01%。价格接近 SMA50（479.78），技术动能改善。
RSI 为 29.3，处于超卖区域；MACD 发生死叉，DIF 线 -0.016 低于信号线 -0.014；价格 6.76 低于 SMA20（6.79）、SMA50（6.83）和 SMA200（6.98），空头排列明显。近一日微跌 0.05%，但技术指标一致指向下行。
MACD 出现金叉，DIF 线 8.77 高于信号线 5.73；但价格 441.31 在近一日下跌 4.17%，RSI 59.9 处于正常区域。趋势中性，价格位于 SMA20（421.28）和 SMA50（405.44）之上但低于 SMA200（457.76），多空信号混合。
VIX 恐慌指数
10Y 美债收益率 (%)
美元指数 DXY
S&P 500 ETF
Nasdaq 100 ETF
Apple
Microsoft
Nvidia
Alphabet
Tesla
Meta
Bitcoin
Ethereum
Solana
阿里巴巴 (BABA)
拼多多 (PDD)
京东 (JD)
腾讯控股 (0700.HK)
黄金期货
WTI 原油期货
美元 / 人民币
技术指标解读基于历史数据，过去走势不代表未来表现，仅供技术指标解读参考。投资者应结合基本面和市场环境综合判断，指标信号可能存在偏差或延迟，不构成投资建议。
The US military said strikes on Qeshm Island, in the Strait of Hormuz, were "in response to attempted attacks by Iran across the Middle East".
中文摘要 美军称对伊朗格什姆岛发动「自卫」打击，以回应伊朗在中东的未遂攻击。打击发生在霍尔木兹海峡。
Sydney crowd told to target National MPs as upper house prepares to vote on a bill outlawing sex-selective terminations Follow our Australia news live blog for latest updates Get our breaking news email, free app or daily news podcast One Nation’s Barnaby Joyce has joined pro-life campaigners to pil
中文摘要 澳大利亚政治人物巴纳比·乔伊斯在新南威尔士州选举前集会反堕胎活动人士，敦促目标国家党议员。上议院准备投票禁止性别选择性终止妊娠的法案。
Follow today’s news live Get our breaking news email, free app or daily news podcast Chaney said: AI companies should be able to unlock the majority of global content with a handful of individual deals – in the same way that every other industry licenses copyrighted content. Government could further
中文摘要 澳大利亚政治动态：所罗门群岛总理抵达与安东尼·阿尔巴尼斯进行条约谈判；参议员康罗伊指责胡西克在AUKUS党团投票中「重写历史」。
President Lee Jae Myung came to office after his predecessor, a conservative, was ousted for imposing martial law. Now Mr. Lee’s popularity is projected to ripple across other contests.
中文摘要 韩国选举：总统李在明在前任因实施戒严被罢免后上任，其声望预计将影响其他选举。
Prime Minister Benjamin Netanyahu of Israel vowed to continue Israel’s campaign against Hezbollah, even as Lebanese and Israeli officials met in Washington.
中文摘要 伊朗战争动态：黎巴嫩和谈在华盛顿恢复，同时以色列总理本雅明·内塔尼亚胡誓言继续打击真主党。
中文摘要 无具体信息提供。
The untold story of women on the battlefield.
中文摘要 探讨女性参战的故事，揭示战场上女性的经历。
US military says it struck tanker and sites on Iran’s Qeshm Island and defended Kuwait and Bahrain from missile attacks The US and Iran have exchanged fresh missiles and drone strikes, further jeopardising efforts by Washington to secure a new ceasefire agreement with Tehran. US forces fired a Hellf
中文摘要 美国和伊朗在停火谈判停滞之际互发新一轮打击，美军称袭击了伊朗格什姆岛和油轮，并防御科威特和巴林免受导弹攻击。
Acting Attorney General Todd Blanche's announcement to abandon the fund comes amid pushback from top Republican lawmakers.
中文摘要 特朗普政府放弃18亿美元的「反武器化」基金，代理司法部长托德·布兰奇宣布此决定，此前遭到共和党议员反对。
Press freedom advocates, however, have warned that the dinner could give Trump a podium to attack the news media.
中文摘要 特朗普将出席推迟的白宫记者协会晚宴，此前有枪击事件；新闻自由倡导者警告晚宴可能成为特朗普攻击媒体的平台。
Thai authorities are ramping up enforcement of local ownership rules, stoking anxiety among foreign businesses.
中文摘要 泰国加强执行本地所有权规定，打击利用本地名义的外国公司，引发外国企业担忧。
US President Trump reported to lash out at Israeli PM Netanyahu over Israel’s threat to strike Beirut suburbs.
中文摘要 伊朗战争动态：美军打击伊朗格什姆岛，德黑兰称袭击科威特和巴林；据报道特朗普抨击内塔尼亚胡威胁袭击贝鲁特郊区。
Over the past two decades, Iran repeatedly threatened to close down the waterway. President Trump underestimated Iran’s ability to do so.
中文摘要 霍尔木兹海峡的战争游戏和警告被特朗普忽视；过去二十年伊朗多次威胁关闭该水道，特朗普低估了伊朗的能力。
Syrian commission confirms the deaths of Rania al-Abbasi’s six children, missing under Bashar al-Assad’s rule.
中文摘要 叙利亚委员会确认拉尼亚·阿尔-阿巴斯的六个孩子在巴沙尔·阿萨德统治下失踪并死亡。
A colossal 400-kilogram flag was draped over Rome’s Colosseum as Italy marked the 80th anniversary of its republic.
中文摘要 意大利庆祝民主80周年，一幅400公斤重的巨型旗帜覆盖罗马斗兽场。
President Donald Trump has spent months projecting confidence that a deal to end the Iran conflict is within reach, but Israel's determination to press ahead with its own objectives underscores his tenuous control over the outcome of the crisis. Bloomberg's Michael Heath has the latest. (Source: Blo
中文摘要 特朗普自信伊朗冲突协议可达成，但以色列坚持己见，显示其对危机结果控制力薄弱。
SpaceX aims to raise $75 billion in its initial public offering by selling 555.6 million shares at a target price of $135 per share, Reuters reported, citing an unidentified source familiar with the matter.
中文摘要 SpaceX计划通过IPO融资750亿美元，以每股135美元的价格出售5.556亿股。
Applied Aerospace & Defense Inc., a space and defense engineering firm, raised $650 million in an initial public offering, according to a person familiar with the matter.
中文摘要 Applied Aerospace & Defense公司通过在美国的IPO融资6.5亿美元。
Gold edged lower, after US jobs data reinforced bets that the Federal Reserve will keep interest rates higher for longer.
中文摘要 黄金价格小幅下跌，因美国就业数据强劲，强化了美联储将长时间维持高利率的预期。
A newly-published report suggests a moderate lifestyle in retirement costs £32,700 for one person and £45,400 for two.
中文摘要 报告显示四分之三的工作者未达到“中等”退休金收入，中等退休生活成本单人为3.27万英镑，双人为4.54万英镑。
The Bank of England is asking the public which animals should appear on future banknotes.
中文摘要 英格兰银行询问公众哪些动物应出现在未来纸币上，包括海雀和大黄蜂等18种生物入选候选名单。
Technology committee calls on government to trigger break clause in flashpoint NHS contract
中文摘要 英国议员表示Palantir公司不应在英国公共数据系统中担任“重要角色”，科技委员会呼吁政府触发NHS合同中的终止条款。
UK regulator focuses on teams with partnerships with digital assets companies that are not authorised to operate in Britain
中文摘要 英超俱乐部可能因与加密货币公司的赞助协议面临法律行动，英国监管机构关注与未经授权在英国运营的数字资产公司合作的球队。
Taiwan’s central bank is extending its reach ever deeper into foreign-exchange markets, seeking to ensure currency stability as the artificial intelligence boom intensifies a divide between the island’s tech sector and the rest of the economy.
中文摘要 台湾中央银行深入干预外汇市场，确保货币稳定，因人工智能热潮加剧了岛内科技部门与其他经济部门的分化。
Fund with net assets of $31bn aimed at retail investors limits withdrawals in latest sign of exodus from sector
中文摘要 Cliffwater旗舰私人信贷基金的赎回请求达到17%，该基金净资产310亿美元，针对散户投资者，限制提款，显示该领域资金外流。
Asian stocks followed Wall Street higher as renewed enthusiasm for the artificial-intelligence trade drove US equities to records. The yen hovered near 160 per dollar.
中文摘要 亚洲股市跟随华尔街上涨至新高，因人工智能交易热潮推动美国股市创纪录。日元汇率接近1美元兑160日元。
Oil rose for a third day on pessimism over the prospects of the US and Iran reaching a peace deal and as fresh fighting flared up in the Middle East.
中文摘要 石油价格连续第三天上涨，因美伊和平协议前景悲观，且中东地区爆发新冲突。
17 回复 · 程序员 节点
13 回复 · 程序员 节点
7 回复 · 程序员 节点
22 回复 · 程序员 节点
15 回复 · Apple 节点
6 回复 · 程序员 节点
9 回复 · Apple 节点
4 回复 · Apple 节点
7 回复 · Linux 节点
13 回复 · Apple 节点
还得练啊，都过去一个月了，还没看到无限bug team 随便用 64 个帖子 - 59 位参与者 阅读完整话题
本帖使用社区开源推广，符合推广要求。我申明并遵循社区要求的以下内容： 我的帖子已经打上 开源推广 标签：是 我的开源项目完整开源，无未开源部分：是 我的开源项目已链接认可 LINUX DO 社区：是 我帖子内的项目介绍，AI生成、润色内容部分已截图发出：是 以上选择我承诺是永久有效的，接受社区和佬友监督：是 项目地址： GitHub： github.com GitHub - physics-dimension/PriceAI: AI 订阅渠道比价工具：聚合 ChatGPT、Claude、Gemini、Grok... AI 订阅渠道比价工具：聚合 ChatGPT、Claude、Gemini、Gr
窝不明白，为什么我的舍友们都在谈论着OpenAI账号被封，仿佛碰见了奥特曼，对于天才程序员来说注定了凶多吉少。 舍友们：做好长期斗争准备，500个free号，今天封2个，明天封3个，就算是奥特曼也得封上一年。 而我：（每天紧张地打开CPA_Manager巡检账号）不是哥们，为什么我200个号一个不死啊 44 个帖子 - 38 位参与者 阅读完整话题
挺多号又刷新了额度。让我遇上Bug了？ 准备明天重开公益站 还有人需要吗？ 154 个帖子 - 145 位参与者 阅读完整话题
前段时间已经关门了，现在我又找到了方法，我觉得德国沃达丰这张手机卡是那种你不申请，绝对血亏，会后悔到拍大腿的卡，它的成本已经低到没人性了，低到每年3毛钱就行，你不申请，也许过几天这个羊毛就彻底没了。 最近火热的giffgaff卡，保号都没这么的便宜 全流程时间预估：从申请到激活使用，整个过程顺利的话大约需要 10分钟作用， 遇到问题也不超过24 小时。其中填表和 KYC 认证只需 10-20 分钟，主要等待时间在于官方审核（通常 10 分钟到 24 小时不等，大部分人 1小时内能收到。建议尽早申请，趁政策还没收紧！ 教程如下，从如何注册申请——KYC详细步骤——如何注册绑定账号——如何充值保号
我在很早之前就说过，后面我们会有很多小单子放出来，给大家接来练手，这玩意儿不可能赚不到钱，只是没想到市场变化的这么快，B级的单子做不了了（没市场），起步都是A+，但这也不是问题，全流程我们已经跑通，所以要扩招人员，下半年猛猛冲击高质量的短剧和网络大电影。 1.这次扩招我们需要6名左右的视频制作人员，我们扩招的人一定要有责任心，人品好，技术都可以慢慢打磨，基本跟着流程走一部就很快能学会了，怎么理解“责任心？” 就比如一部剧只有10天的制作周期，每人分配到10-15集，如果交片的质量不行，和做不完15集，我们是需要担责的，违约会扣我们很多钱。【一定不能在你这出了问题，比如大家都在加班熬夜赶片，你说
看了很多强调上下文重要性的文章，用cc接国模愈发不顺手，总感觉cc的上下文屎山是不是越来越大了，于是捡起之前折腾了一半的pi，我的想法和作者部分一致，上下文工程是第一要务，准确的控制注入模型的每一个字肯定能获得比黑盒更舒服更有包裹感(误 。 点进这个帖子的应该或多或少都是听说过pi的，如果不了解请看作者的文章 agent，无 MCP、无后台 bash、无内置 to-do、无 plan mode、无子 agent，本体的内置提示词不超过1000token，仅内置4 个工具：read、write、edit、bash 关于package是什么 在pi中，Package 可以是： Extension：
前女友好像经常半夜跑电报，我想知道她来电报做啥？有没有知道的？二次元？看片？还是啥。 113 个帖子 - 86 位参与者 阅读完整话题
目前手中有GG,德国沃达丰，O2,美国手机卡，如果有护照的，强烈建议德国沃达丰和O2,买个小白卡成本20多元，但是可以写入6个手机号，目前我申请了3个沃达丰和3个02，使用wise定时保号，沃达丰一个月充值0.01元，o2目前充值0.01，官网变成一年保号一次就可以，所以6个号一年成本就2块人民币左右，最不推荐的就是GG 85 个帖子 - 40 位参与者 阅读完整话题
人家的订阅都是用量用完了限制使用，他MiniMax浓眉大眼的是接着奏乐接着舞，给你直接扣余额。 扣余额吧就扣余额，你余额是0的他还能给你扣成负的。 放眼世界应该没第二家了吧？ 问客服，有没有开关可以控制，切换到正常的模式，问就是没有。 欠费是没多少，就一块多，但是无语是挺无语的。 46 个帖子 - 27 位参与者 阅读完整话题