Python · ★ 9,741 · 🍴 644 · 📈 3,530 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 Headroom是一个压缩工具，用于在输出发送给大语言模型（LLM）前压缩工具输出、日志、文件和RAG数据块。它能减少60-95%的token使用，同时保持答案质量，提供库、代理和MCP服务器形式。适用于需要优化LLM输入、降低成本的开发者和系统，特别在处理大量数据时提升效率。
JavaScript · ★ 205,745 · 🍴 31,589 · 📈 2,141 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是一个代理性能优化系统，针对Claude Code、Codex、Opencode、Cursor等AI代理。它提供技能、本能、记忆和安全功能，采用研究优先的开发方法。适用于开发者和研究人员优化AI代理的性能和效率，尤其在编码和研究场景中提升自主性和可靠性。
Go · ★ 35,399 · 🍴 416 · 📈 24 stars today
Find vulnerabilities, misconfigurations, secrets, SBOM in containers, Kubernetes, code repositories, clouds and more
中文介绍 Trivy是一个安全扫描工具，用于检测容器、Kubernetes、代码仓库和云环境中的漏洞、错误配置、密钥和软件物料清单（SBOM）。它集成到DevSecOps流程中，帮助团队在开发和部署阶段识别安全风险，确保系统安全，适用于云原生应用和基础设施管理。
Python · ★ 179,127 · 🍴 30,687 · 📈 1,735 stars today
The agent that grows with you
中文介绍 Hermes Agent是一个自适应代理，能够随着用户使用而成长。它可能基于机器学习技术，根据交互不断优化自身行为，提供个性化助手功能。适用于需要持续改进支持的用户，在日常任务、学习或工作中提供自适应帮助。
Python · ★ 142,866 · 🍴 9,764 · 📈 1,984 stars today
Python tool for converting files and office documents to Markdown.
中文介绍 MarkItDown是一个Python工具，用于将文件和办公文档（如Word、Excel）转换为Markdown格式。它简化了文档处理流程，适用于开发者、内容创作者和需要将多种文档统一为Markdown的场景，便于版本控制、协作和知识管理。
Python · ★ 13,100 · 🍴 1,593 · 📈 719 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Web界面，提供最佳方式从网页或手机访问代理功能。它使用户能通过浏览器或移动设备便捷使用Hermes Agent，实现跨平台交互，适用于移动办公、远程访问和实时助手场景。
Python · ★ 60,244 · 🍴 5,807 · 📈 1,067 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Web爬虫框架，能处理从单个请求到大规模爬取的各种任务。它提供灵活的爬取策略和数据解析功能，适用于数据科学家、开发者和研究人员，用于从网站收集数据进行分析、研究或商业智能应用。
Java · ★ 23,271 · 🍴 2,183 · 📈 570 stars today
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
中文介绍 OpenDataLoader PDF是一个PDF解析器，专为AI就绪数据设计。它自动化PDF的可访问性处理，提取结构化内容，开源可用。适用于AI开发者、数据分析师和需要从PDF文档中提取文本、表格和图像的场景，以便于机器学习和数据预处理。
Python · ★ 51,931 · 🍴 32,642 · 📈 29 stars today
Odoo. Open Source Apps To Grow Your Business.
中文介绍 Odoo是一个开源的企业应用套件，用于帮助企业成长。它提供包括CRM、电商、会计、库存等多种模块，基于Python开发。适用于中小企业和大型企业，通过集成化应用提升业务管理效率，支持定制化部署和云端使用。
Python · ★ 8,960 · 🍴 1,106 · 📈 693 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是一个开源项目，允许用户通过免提语音交互与任何大语言模型对话，支持语音打断和Live2D面部动画，可在本地跨平台运行。适用于VTuber、直播主播和开发者，提供沉浸式AI交互体验，增强娱乐和内容创作。
★ 349,010 · 🍴 83,155 · 📈 330 stars today
A complete computer science study plan to become a software engineer.
中文介绍 Coding Interview University是一个完整的计算机科学学习计划，旨在帮助学习者成为软件工程师。它涵盖算法、数据结构、系统设计等主题，提供资源列表和学习路径。适用于准备技术面试、转行软件工程或自学编程的初学者和进阶者。
Jupyter Notebook · ★ 18,902 · 🍴 2,071 · 📈 208 stars today
AirLLM 70B inference with single 4GB GPU
中文介绍 AirLLM使得在单张4GB显卡上运行70B参数的大语言模型推理成为可能。它通过优化模型加载和计算效率，降低硬件门槛。适用于资源有限的开发者和研究人员，能够在消费级GPU上部署和测试大型模型，用于研究和原型开发。
TypeScript · ★ 25,175 · 🍴 2,213 · 📈 600 stars today
Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.
中文介绍 SuperMemory是一个极速、可扩展的记忆引擎和应用，提供AI时代的记忆API。它用于存储和检索信息，支持上下文管理和个性化响应。适用于AI系统、聊天机器人和需要长期记忆功能的应用，提升交互的连贯性和用户体验。
Python · ★ 9,920 · 🍴 2,004 · 📈 197 stars today
"Vibe-Trading: Your Personal Trading Agent"
中文介绍 Vibe-Trading是一个个人交易代理，利用AI技术辅助交易决策。它可能结合市场数据分析和用户偏好，提供自动化或半自动化的交易策略。适用于个人投资者和交易员，帮助优化投资流程，基于实时数据和趋势进行智能操作。
@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 指出当前基于嵌入向量的AI Agent记忆系统存在根本缺陷，会遗忘已存储信息并虚构未存储内容，提出了基于拓扑结构的新解法以规避遗忘问题。
@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 探讨AI时代下，专业深度与知识广度之间的传统权衡被改变。AI工具使得个人能同时根据任务需求，在特定领域进行深度挖掘和在不同领域间快速切换。
@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 提供了一份关于“企业上下文层”的实用指南，解释它是什么、不是什么，以及在企业AI架构中的具体定位，旨在厘清常见的认知混淆。
@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 分享了一个真实的安全案例：通过一个恶意网站成功攻击了知名主播PewDiePie自托管的AI Agent系统，随后又帮助其修复了该漏洞。
@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 反思了自己早期构建一个庞大代码库（50万行Rails代码）的经历，批评这种为AI Agent构建僵化、低效“富士康工厂”式系统的方式，并主张更智能的构建思路。
@mem0ai · 17.6K 粉丝 · 82.8K 阅 · 520 赞 · 60 转
Agent harnesses are where AI software actually runs. Cursor, Devin, Claude Code, Codex: these environments handle context, orchestrate tools, coordinate agents, and increasingly, manage memory. The
中文介绍 分析了AI Agent运行环境（如Cursor、Devin、Claude Code）中记忆管理的现状，指出这是当前技术栈的关键层，并概述了相关工具与挑战。
@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 介绍了Claude Code新推出的动态工作流功能，允许AI根据具体任务实时生成并运行定制化的执行流程，从而扩展其应用场景。
@drfeifei · 738.0K 粉丝 · 72.2K 阅 · 699 赞 · 144 转
“The world is everything that is the case.” — Ludwig Wittgenstein, Tractatus Logico-Philosophicus, 1921 The world is not made of words. In an earlier essay, we argued that spatial intelligence is AI’s
中文介绍 引用维特根斯坦哲学，提出建立“世界模型”的功能性分类法，强调AI不仅需要语言智能，更需要空间智能来理解真实物理世界。
@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 总结了过去60天在Agentic工程中使用的技巧，延续此前关于Claude Code的分享，强调使用计划文件（plan.md）和语音指令作为核心工作流。
@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 分享使用Hermes Analyst Agent两个月后的六点经验教训，指出Agent失败通常不是因为智力不足，而是在任务协调与管理上出现问题。
@OptimaiNetwork · 98.8K 粉丝 · 5.7K 阅 · 542 赞 · 110 转
May was an important month for OptimAI because it marked a shift from proving the product to expanding the platform. The broader market is moving in the same direction: AI is no longer just about
中文介绍 发布了OptimAI网络的月度总结，概述了五月从产品验证转向平台扩展的战略进展，并指出行业正朝着构建Agent原生互联网的方向发展。
Verified Generation and Compounding Intelligence
中文介绍 Carina Hong 和 Axiom Math 探讨 AI 扩展超越非正式 AI，涉及验证生成和复合智能。
The legendary Microsoft CEO makes his first Latent Space appearance!
中文介绍 微软首席执行官萨提亚·纳德拉在 Microsoft Build 上首次亮相 Latent Space 特别节目，讨论 AI 相关话题。
GPT-Rosalind advances life sciences research with enhanced biological reasoning, medicinal chemistry expertise, genomics analysis, and experimental workflow capabilities.
中文介绍 OpenAI 介绍 GPT-Rosalind 的新能力，该模型通过增强生物推理、药物化学专业知识、基因组学分析和实验工作流程能力，推动生命科学研究。
中文介绍 Hugging Face 博客讨论直接偏好优化技术在聊天机器人之外的应用。
See how Wasmer used Codex with GPT-5.5 to build a Node.js runtime for the edge, accelerating development 10x to 20x and shipping in weeks instead of months.
中文介绍 Wasmer 利用 Codex 和 GPT-5.5 构建边缘 Node.js 运行时，开发速度提升 10 到 20 倍，并在数周内完成交付，而非数月。
OpenAI outlines its public policy agenda for AI, including safety, youth protection, workforce transition, and global standards to ensure AI benefits society.
中文介绍 OpenAI 概述其 AI 公共政策议程，涵盖安全、青年保护、劳动力转型和全球标准，以确保 AI 造福社会。
OpenAI outlines a blueprint for U.S. governance of frontier AI, proposing a federal framework for safety, resilience, and national security.
中文介绍 OpenAI 提出前沿 AI 民主治理蓝图，建议美国联邦框架以确保安全、韧性和国家安全。
Microsoft Build recap, and new MAI model technical details
中文介绍 Microsoft Build 回顾，介绍 MAI-Thinking-1 和 MAI 系列模型的新技术细节。
中文介绍 Hugging Face 博客介绍为 Reachy Mini 添加 MCP 工具的方法。
中文介绍 TLDR AI 总结 Codex 站点、微软模型和 Anthropic 成本反弹的相关内容。
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 通过 Copilot 开创了现代 AI 编码时代，代理编码的激增给平台带来压力，GitHub 制定了相应计划，由 Kyle Daigle 介绍。
中文介绍 Hugging Face 博客介绍 Holo3.1，一种快速和本地的计算机使用代理。
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 与 OpenAI 合作构建 AI 驱动的索赔助手，在全国范围内部署，指导客户提交索赔，提供 24/7 支持，并在需求高峰时扩展运营。
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 全球医疗保健部门面临压力，长期投资不足和招聘限制与人口老龄化需求激增同时发生，导致护理提供碎片化，代理 AI 可能有助于重新人性化医疗保健。
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 介绍 Codex 的新插件、站点和注释，帮助分析师、营销人员、设计师、投资者等团队利用 AI 提高工作效率。
第一作者: Jonas Guan · 方向: AI 安全
AI安全计算机蠕虫大语言模型自适应攻击零成本攻击
Abstract:A computer worm is malware that spreads on a network by replicating itself from one machine to another. Traditional worms, like WannaCry, exploited predetermined vulnerabilities, and their spread can be halted by patching those vulnerabilities. Here we show that artificial intelligence (AI) agents enable a fundamentally new threat: a worm that generates tailored attack strategies to each target it encounters. The worm parasitically uses compromised machines to run open-weight large language models (LLMs) to sustain its reasoning, or extend its reach for further attacks. Deployed on a network of machines spanning Linux, Windows, and IoT (Internet of Things) devices, the worm propagated by exploiting common, real-world corporate network vulnerabilities. Since the worm is powered by stolen compute, the attacker's marginal cost per new infection is zero. This creates a...
论文介绍 传统计算机蠕虫利用固定漏洞传播，修补后即可遏制。本文揭示了一种由AI代理驱动的新型威胁：一种能针对每个入侵目标生成定制化攻击策略的自适应蠕虫。该蠕虫寄生性地使用被攻陷的机器运行开源大语言模型来维持其推理能力，从而在网络中持续传播。由于攻击者利用的是被盗算力，感染新机器的边际成本为零，这显著增加了防御难度。
第一作者: Marco Benedetti · 方向: 软件安全
神经网络抗碰撞性算法复杂性阈值行为二进制输出
Abstract:We initiate the study of the algorithmic complexity of finding collisions in single-layer binary neural networks. Given a random matrix $\mathbf{A} \in \mathbb{R}^{m\times n}$, an input $\mathbf{x} \in \{-1,1\}^n$ is mapped to a binary output vector $\varphi(\mathbf{A}\mathbf{x})\in \{-1,1\}^m$, where $\varphi$ is an activation function with constant behavior on $[\kappa, \infty)$ for some threshold $\kappa \geq 0$. We identify the threshold scale $\kappa=\Theta(1/\sqrt{\alpha})$, where $\alpha=m/n$, as separating two complementary phenomena. When $\kappa \ll 1/\sqrt{\alpha}$, we give a simple online algorithm that efficiently produces extensive collisions. When $\kappa \gg 1/\sqrt{\alpha}$, for a natural \emph{randomized} non-periodic activation and suitable oscillation complexity, we prove that the extensive-collision space exhibits an overlap gap property (OGP), yielding an...
论文介绍 本文研究在单层二进制神经网络中寻找碰撞的算法复杂性问题。研究发现，一个关键的阈值尺度决定了两种互补现象：当激活阈值远低于此尺度时，存在高效的在线算法能产生大量碰撞；当阈值远高于此尺度时，对于特定的随机激活函数，其碰撞空间会表现出重叠间隙性质。这为理解神经网络的安全特性提供了理论基础。
第一作者: Samuel Breckenridge · 方向: 密码学协议
可验证凭证隐私保护大语言模型去中心化对抗性示例
Abstract:Decentralized verifiable credential systems have seen limited deployment in practice. Existing constructions, built on zero-knowledge proofs, are complex, application-specific, and largely restricted to predicates over structured data. We present Privately Inferred Credentials ($\pi$Creds): privacy-preserving, legacy-compatible, decentralized verifiable credentials generated by trusted LLM inference over authenticated data. LLMs' ability to semantically reason over unstructured data substantially expands the range of claims $\pi$Creds can certify over existing credential systems. The use of LLMs also introduces new application-level threats, which we formalize through two problems: the Source-Constrained Adversarial Example (SCAE) problem, which captures robustness against adversaries that manipulate authenticated data to obtain misleading credentials, and the Authenticated...
论文介绍 现有基于零知识证明的去中心化可验证凭证系统复杂且应用特定。本文提出「隐私推断凭证」（πCreds），利用可信大语言模型对认证数据进行推理，生成隐私保护的凭证。LLM的语义推理能力大幅扩展了可认证声明的范围。同时，该方法也引入了新的应用层威胁，例如攻击者可能操纵认证数据以获取误导性凭证，本文对此形式化了相关安全问题。
第一作者: Jianwei Tai · 方向: 安全研究
机器人安全视觉语言动作策略部署安全可执行策略动作解归一化
Abstract:Vision-language-action (VLA) policies are often treated as checkpoint-defined objects: if the weights, prompt, and benchmark suite match, the deployment is assumed to be the same policy. Robot execution breaks this assumption because the same normalized model output can become a different physical action after action unnormalization and controller conventions are applied. This creates a deployment-safety gap: safety review can certify the checkpoint while missing the executable robot policy that reaches the controller. We formalize this gap as an executable policy specification problem: a VLA policy includes the learned model, action representation, metadata-selected unnormalizer, and controller-facing conventions. Under this view, identical checkpoints can be executable-inequivalent. For quantile-style action normalization, we derive a closed-form metadata mismatch transform...
论文介绍 视觉语言动作策略常被视为由权重和提示定义的对象，但机器人执行时，相同的模型输出经解归一化和控制器转换后可能对应不同的物理动作，这造成了「部署安全缺口」。本文将此形式化为可执行策略规范问题，并指出相同的检查点可能产生不等价的可执行策略。研究推导了在特定归一化方式下元数据不匹配的变换公式，以量化分析该安全缺口。
第一作者: Emmanuele Massidda · 方向: 密码学协议
恶意软件检测隐私设计Android安全用户信任设计需求
Abstract:Android malware detection increasingly relies on collecting and processing sensitive user data, including device identifiers, network artifacts, and runtime traces, while privacy is too often treated as a secondary concern. Existing privacy-aware approaches typically enforce privacy after data collection, for example, through anonymization, encryption, or federated learning, yet still require access to user information and therefore demand a high level of user trust in systems that already operate with privileged access to device activity. We argue that this requirement should be removed rather than managed. Android malware detection should be privacy-aware by design, so that effective analysis does not depend on sensitive data being accessed in the first place. To this end, we first formalize a set of design requirements for privacy-by-design detection and then implement each...
论文介绍 现有Android恶意软件检测通常在数据收集后才施加隐私保护（如匿名化），但仍需访问敏感用户数据，依赖用户信任。本文主张恶意软件检测应从设计之初就具备隐私意识，无需访问敏感数据即可进行有效分析。为此，研究首先形式化了一套隐私设计检测的设计需求，并实现了相应的检测管道。
第一作者: Zhenyu Yu · 方向: 隐私保护
轨迹隐私不可学习例子流形对齐兴趣点预测净化对抗
Abstract:A publisher who releases check-in trajectories inadvertently publishes a strong predictor of every user's future locations. We address this risk by generating unlearnable trajectories, perturbed sequences that yield victim models with degraded next-Point-of-Interest (next-POI) accuracy on clean test inputs. Direct ports of image-domain unlearnable examples fail on two counts. The published data must remain geographically and semantically plausible, and the perturbation must resist purification adversaries that exploit the structure of randomized defences. We propose Ghost, a manifold-aligned framework whose perturbations look like plausible human check-in sequences yet leave no learnable signal behind. Ghost steers each substitution onto the real-trajectory manifold through a frozen trajectory language model, so a denoising-bridge adversary has nothing to invert and a...
论文介绍 发布的出行轨迹可被用于精准预测用户的未来位置。直接移植图像领域的不可学习例子方法面临数据需保持地理语义合理且扰动能抵抗净化对抗者的挑战。本文提出Ghost框架，通过对齐到真实轨迹流形生成看似合理但无法让模型学习的轨迹。它通过冻结的轨迹语言模型引导扰动，使净化对抗者无法利用数据结构进行逆向。
第一作者: Vincent Limbach · 方向: AI 安全
大语言模型安全对抗攻击越狱评估黑盒攻击鲁棒性评估
Abstract:Accurately evaluating adversarial robustness is a longstanding challenge. A flawed attack design can inflate robustness estimates, making deployment risk assessment and defense comparison unreliable. Historically, standardized attacks such as AutoAttack have largely resolved this for image classifiers, providing a reliable evaluation baseline for systematic comparison across defenses. However, no equivalent exists for LLM jailbreak evaluation yet, where designing such an attack is considerably more difficult. A reliable attack must, among other things, be black-box compatible, applicable to arbitrary defense pipelines, and efficient, which no existing method jointly satisfies. We introduce Indirect Harm Optimization (IHO), a masked diffusion language model attacker trained via iterative preference optimization against a harmfulness judge, requiring only black-box access to the...
论文介绍 准确评估大语言模型的对抗鲁棒性是一项挑战。目前缺乏用于越狱评估的标准化攻击方法。本文提出「间接有害优化」攻击，它使用一个经过训练的掩码扩散语言模型作为攻击者，仅需黑盒访问目标LLM和一个有害性判别器。该攻击被设计为黑盒兼容、适用于任意防御流程且高效，旨在为LLM安全评估提供一个可靠的基准。
第一作者: Vincenzo Sammartino · 方向: 密码学协议
6G网络工业物联网数字孪生后量子密码联邦学习
Abstract:Sixth-generation (6G) wireless networks will underpin ultra-dense Industrial IoT (IIoT) ecosystems in which resource-constrained Far-Edge devices -- autonomous mobile robots, industrial actuators, connected vehicles -- must simultaneously satisfy sub-millisecond latency, $10^{-7}$-class reliability, and decades-long cryptographic security. Current architectures delegate Digital Twin (DT) computation to centralised cloud or Mobile Edge Computing (MEC) servers, incurring prohibitive round-trip latency, and rely on classical public-key cryptography vulnerable to quantum attacks under the harvest-now, decrypt-later (HNDL) threat model. We propose Q-FE, a Quantum-Native 6G Far-Edge architecture integrating three co-designed components: (i) Micro-Digital Twins ($\mu$DTs) co-located with 6G base stations and high-capability endpoints; (ii) a Cross-Layer Post-Quantum Key Exchange...
论文介绍 6G网络将支撑超密集工业物联网，其中资源受限的远端设备需要满足超低时延和长期抗量子安全。当前架构将数字孪生计算集中化，时延高，且依赖易受量子攻击的密码体系。本文提出Q-FE量子原生6G远端架构，整合了与6G基站共置的微数字孪生、基于CSIDH的后量子密钥交换以及异步联邦学习三个协同设计组件。
第一作者: Malia Barker · 方向: 软件安全
大语言模型算术推理数字重映射泛化测试安全
Abstract:Large language models achieve strong performance on arithmetic reasoning benchmarks, and one common response to arithmetic brittleness is to delegate computation to code. Yet models are still often used in settings where they must reason directly from natural language, and trustworthy models should solve small-number arithmetic word problems without external tools. Prior work shows that LLMs are sensitive to numerical variation: a model may solve an original problem but fail on structurally similar variants requiring the same reasoning procedure with different numbers. We ask whether this fragility persists under a stricter setting involving small, schema-preserving numeric changes that retain the original reasoning program and avoid large-number stress tests. We introduce an automatic algorithm for generating numeric-remapping attacks on arithmetic word problems. Unlike...
论文介绍 研究大型语言模型在算术推理中的泛化能力，特别是数字变化导致的脆弱性。引入自动数字重映射攻击算法，生成结构相似但数字不同的小规模问题变体，测试模型在保留原始推理程序时的表现。该方法评估模型在无外部工具辅助下的可靠性，适用于自然语言推理场景。
第一作者: Atsu Kokuvi Angélo Passah · 方向: 隐私保护
信道图表位置隐私地理不可区分性拉普拉斯机制隐私保护
Abstract:Channel charting enables location-based services (LBSs) without requiring explicit position information by using pseudo-locations from the channel chart. While this property implies inherent privacy advantages, it does not provide formal privacy guarantees. In this work, we address location privacy in channel charting referred to as chart location indistinguishability (CLI), which extends geo-indistinguishability (GI) to channel charting representations. In order to achieve CLI, a standard planar Laplace mechanism is investigated and a geometry-aware Mahalanobis norm planar Laplace (MNPL) mechanism is devised. The proposed MNPL mechanism perturbs the channel chart by injecting noise aligned with the local structure of the chart. In the CLI framework with MNPL, privacy is defined in latent channel chart manifolds using locally adaptive covariance derived from chart...
论文介绍 针对信道图表中的位置隐私问题，将地理不可区分性扩展至图表表示，提出几何感知的MNPL机制。该机制通过注入对齐图表局部结构的噪声，实现图表位置不可区分性，在形式化隐私保障下支持基于位置的服务。
第一作者: Elias Lunderbye · 方向: 网络安全
入侵检测系统RPL网络物联网基础模型攻击识别
Abstract:AI-based intrusion detection systems (IDS) have shown promise in detecting attacks on IoT systems. In this work, we explore the use of foundation models to detect and identify attacks, with a specific focus on RPL-based IoT networks. We study multiple attack types, attack variations, and network configurations, and provide insights into the performance of foundation models for attack identification. Specifically, we fine-tune the MOMENT foundation model for multi-class attack identification. Our evaluation is based on a dataset containing RPL-related statistics collected under normal operation and under Blackhole, DIS flooding, Worst Parent, and Local Repair attacks, generated in a Cooja simulation environment. The initial results are promising. The approach achieves attack-detection performance comparable to state-of-the-art methods, while also demonstrating strong...
论文介绍 探索使用基础模型为RPL-based物联网网络构建入侵检测系统。通过微调MOMENT基础模型，在模拟数据集上识别多种攻击类型，如Blackhole和DIS flooding。该方法在攻击检测性能上与现有技术相当，能处理多样网络配置，提升物联网安全监控。
第一作者: Peter Williams · 方向: 软件安全
APT恶意软件归因二元分类器闭集分类韧性
Abstract:Early attribution of Advanced Persistent Threat (APT) activity can help defenders prioritise investigation, select countermeasures, and reduce the impact of an intrusion. Malware provides useful attribution evidence, but automated APT malware attribution remains difficult in practice. Existing approaches are typically trained and evaluated as closed-set classifiers over a limited number of known APT groups. In operational environments, however, classifiers are likely to encounter samples from groups not represented during training. Closed-set classifiers are then forced to assign such samples to known groups, producing unsupported and potentially misleading attributions. We present a high-precision APT malware attribution method based on ranked binary classifiers with explicit abstention. Rather than training a single multi-class classifier, our approach trains and tunes two...
论文介绍 提出高精度APT恶意软件归因方法，基于排名二元分类器，允许在不确定时放弃归因。针对闭集分类器在面对训练外样本时的错误分配问题，该方法提升对未知攻击组的韧性，增强操作环境中的归因可靠性。
第一作者: Yufei Zhou · 方向: 密码学协议
全同态加密图像处理隐私保护梯度计算高分辨率图像
Abstract:With growing emphasis on privacy protection, homomorphic encryption (HE) has emerged as a core method for privacy-preserving image processing, as it enables operations directly on encrypted data. However, existing research predominantly focuses on low-resolution image processing, and techniques for privacy-preserving high-resolution image processing remain underexplored. As the image size increases, the HE parameters must be adjusted accordingly, and directly applying existing methods can lead to significant computational overhead. In this work, we propose a multi-ciphertext privacy-preserving framework for large images, enabling efficient image encryption and computation under the semi-honest model. Specifically, we divide the large image into multiple sub-images, which allows us to maintain smaller HE parameters and reduce key size. By parallel processing the sub-image...
论文介绍 解决高分辨率图像在隐私保护下的梯度计算挑战。提出多密文框架，将大图像分块处理，使用全同态加密在加密数据上并行计算。该方法降低计算开销和密钥大小，适用于隐私敏感场景如医疗影像分析。
第一作者: Wenqi Chen · 方向: 软件安全
大语言模型安全代码生成自博弈决策树漏洞检测
Abstract:While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data. Current alignment techniques, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), typically apply coarse-grained optimization at the sequence level. This approach often fails to address the localized nature of security flaws, where a single incorrect token choice can compromise an entire program. To bridge this gap, we introduce Tree-like Self-Play (TSP), a framework that reframes secure code generation as a fine-grained sequential decision process. Unlike standard methods that blindly maximize likelihood, TSP constructs a decision tree where the model explores branching trajectories--generating both secure "golden paths" and vulnerable variants. By treating code generation as a self-play game, the...
论文介绍 针对大语言模型代码生成中易复制训练数据漏洞的问题，引入树状自博弈框架。将安全代码生成建模为细粒度序列决策过程，通过构建决策树探索安全和脆弱路径，从错误中学习以提升代码安全性。
第一作者: Zhongyang Lin · 方向: AI 安全
大语言模型越狱防御安全变体表示一致性运行时防御
Abstract:Large language models remain vulnerable to jailbreak attacks that hide harmful intent behind seemingly ordinary requests such as role-play, translation, encoding, adversarial suffixes, and multi-turn buildup. Existing defenses still struggle to handle these attacks without over-blocking benign but sensitive requests, partly because they often apply the same action to every prompt and therefore fail to balance safety and helpfulness. We propose NeuroArmor, a white-box runtime defense that uses prompt-specific safe variants as a local safety reference for deciding when intervention is needed and, once triggered, as safe targets for intervention. For each prompt, NeuroArmor builds K safe variants, compares the prompt state against this local safe reference in hidden-state space, and routes anomalies either to a refusal branch for malicious prompts or to a helpful recovery branch...
论文介绍 提出NeuroArmor白盒运行时防御机制，应对大语言模型的越狱攻击。为每个提示构建安全变体，在隐藏状态空间进行比较，检测异常并选择性地拒绝或恢复，平衡安全性和有用性，避免过度阻塞敏感请求。
第一作者: Farooq Shaikh · 方向: 软件安全
多智能体系统漏洞利用检测工程渐进评估网络安全
Abstract:Vulnerability disclosure volumes now far exceed organizational assessment capacity, yet three adjacent research communities (proof-of-concept generation, vulnerability prioritization, and detection rule engineering) operate largely in isolation. Existing automated exploit generation systems report binary pass/fail outcomes, discarding partial progress and producing no signal for the other two communities. This paper presents FORGE, a multi-agent system that bridges these three silos through graduated exploitation depth. Five specialized agents (Intel, Generator, Planner, Exploit, and Detector) execute in a fixed pipeline that (1) generates targeted vulnerable applications from CVE metadata, (2) conducts coached, multi-turn exploitation assessed by an LLM-primary oracle on a four-level taxonomy (L0: no evidence through L3: full compromise), and (3) produces Sigma and Snort...
论文介绍 针对漏洞披露量超过组织评估能力的问题，提出FORGE多智能体系统。通过五个专门智能体桥接漏洞利用生成、优先级和检测规则工程，进行渐进式利用评估并输出检测规则，提升漏洞响应效率。
第一作者: Hasret Ozan Sevim · 方向: 区块链安全
投机性预言机可提取价值最大可提取价值Layer-2去中心化金融交易垃圾邮件
Abstract:A new form of Maximal Extractable Value (MEV), termed speculative MEV, has emerged across Layer-2 blockchains. Unlike Ethereum mainnet, many Layer-2 systems lack a public mempool, forcing extraction strategies to become probabilistic: searchers emit multiple identical transactions hoping to capture an opportunity first. This generates substantial transaction spam, increasing fees and wasting block space. We investigate speculative Oracle Extractable Value (OEV), a form of MEV associated with liquidating undercollateralized loans via speculative backrunning of oracle price updates. We propose a methodology for detecting speculative liquidations in the wild and apply it across Arbitrum, Base, and Optimism. On October 10, 2025, we identify 64 speculative liquidators on Aave (57% of all detected liquidators) and 831 successful speculative liquidations (39% of all successful...
论文介绍 本文研究了一种在二层网络（Layer-2）上出现的新型最大可提取价值（MEV）——投机性预言机可提取价值。由于许多L2缺乏公开内存池，投机者通过发送大量相同交易来概率性地抢先获利。研究聚焦于通过投机性尾随交易来清算贷款的场景，并提出了在实际链上检测此类投机性清算的方法，揭示了跨链环境下新的安全与效率挑战。
第一作者: Raja Khurram Shahzad · 方向: 软件安全
恶意软件分类特征融合API调用n-gram投票集成
Abstract:The number of malware (either variant or novel) is rapidly increasing, making malware detection and mitigation a complex problem. One approach to improving malware mitigation is automatic detection and malware family classification. However, traditional malware detection methods cannot classify detected malware into their respective families, hindering effective malware mitigation. Consequently, this paper proposes a method to automate malware detection and classification of the detected malware into respective malware families. The proposed method uses feature fusion after extracting relevant malware features such as API calls and fixed and variable length n-grams with a customized feature selection method. Moreover, for the predictive model, a voting based approach is proposed for algorithm fusion. For the experimental evaluation of the proposed method, both binary and...
论文介绍 本文提出了一种用于自动化恶意软件检测及家族分类的混合方法。针对传统方法难以识别恶意软件家族的问题，该研究在提取API调用和n-gram等特征后，采用自定义的特征选择方法进行融合，并提出基于投票的算法融合策略进行预测。该方法旨在提升恶意软件缓解的效率。
第一作者: Maxime Schwarzer · 方向: AI 安全
模型窃取攻击身份无关防御流匹配能源系统入侵检测系统
Abstract:Artificial Intelligence (AI)-based Intrusion Detection Systems (IDS) deployed in energy infrastructure are vulnerable to model theft attacks, which allow adversaries to create evasive traffic offline. Current defences against model extraction rely either on identity-bound query monitoring, which is ineffective against distributed attackers (Sybil), or on prediction poisoning through soft-label perturbation, which is inapplicable to hard-label IDS deployments. Therefore, we propose FlowGuard, an identity-independent defence based on flow matching that classifies incoming queries as out-of-distribution (OOD) prior to IDS processing. This approach exploits the fact that queries generated synthetically for data-free model stealing attacks occupy a lower-dimensional manifold than real network traffic. This results in measurably lower log-likelihoods when using a Continuous...
论文介绍 本文针对部署在能源基础设施中的AI入侵检测系统（IDS）易受模型窃取攻击的问题，提出了FlowGuard防御方法。该方法不依赖于查询者身份，而是利用流匹配技术，在IDS处理前对查询进行分布外检测，以识别用于数据自由模型窃取的合成查询，从而保护模型免遭窃取。
第一作者: Wan-Hsuan Hsu · 方向: AI 安全
智能合约漏洞检测专家标注数据集去中心化金融大语言模型细粒度标签
Abstract:Smart contract vulnerabilities in Decentralized Finance (DeFi) protocols resulted in over 1.49 billion USD in confirmed losses in 2024 alone, across 192 incidents [1]. As LLM-based vulnerability detection emerges as a promising approach to address these threats, the quality of evaluation datasets has become a critical bottleneck. Existing datasets suffer from three fundamental problems: they are built on outdated Solidity versions (e.g., v0.4) that no longer reflect modern DeFi contracts [5][6][7]; they rely on automated or LLM-generated annotations that introduce hallucination-driven label noise [9][10]; and they apply coarse single-layer labeling that fails to capture the semantic complexity of real-world business logic vulnerabilities [6][7][11][12]. We present Bastet, an expert-labeled DeFi smart contract vulnerability dataset that addresses all three problems through...
论文介绍 本文介绍了Bastet，一个用于检测去中心化金融（DeFi）智能合约漏洞的细粒度专家标注数据集。研究指出现有数据集存在基于过时Solidity版本、依赖自动标注引入噪声以及标签粗粒度等三大问题。Bastet通过采用现代合约、专家标注和细粒度多层次标签来应对这些挑战，以支持基于大语言模型的漏洞检测研究。
第一作者: Aminu Muhammad Auwal · 方向: AI 安全
网络攻击预测差距优先级框架数据集过时模型可解释性对抗鲁棒性
Abstract:While AI and machine learning for cyber attack prediction have advanced, a critical gap persists between theoretical research and practical operational deployment. Building on Ankalaki et al. (2025), this paper provides a comprehensive analysis of 150+ benchmark datasets and 200+ studies to identify and prioritize five implementation hurdles: (1) temporal dataset obsolescence, (2) narrow attack scope, (3) real-time model interpretability, (4) inadequate adversarial robustness, and (5) privacy/ethical concerns. We introduce a novel gap-prioritization framework that evaluates these limitations based on detection impact, implementation cost, and remediation time. Our analysis identifies dataset obsolescence and adversarial robustness as the highest-priority gaps, while highlighting model interpretability as the most cost-effective path for resource-constrained environments. To...
论文介绍 本文分析了AI在网络攻击预测中从理论研究到实际部署的差距。通过综合分析超过150个基准数据集和200项研究，论文识别并优先排序了五个关键实施障碍：数据集时效性、攻击范围狭窄、实时模型可解释性、对抗鲁棒性不足以及隐私伦理问题，并提出了一个差距优先级评估框架。
第一作者: Maxime Schwarzer · 方向: AI 安全
模型提取攻击单客户端假设分布式攻击指挥与控制CerberusAI
Abstract:Ensuring the protection of Artificial Intelligence (AI) models deployed in military Command and Control (C2) systems and critical infrastructure is essential for maintaining information superiority. Model Extraction Attacks (MEAs) pose a significant threat, as they enable adversaries to replicate proprietary models, compromise protected information, and prepare offline adversarial attacks. However, current defense strategies predominantly rely on the Single Client Assumption (SCA), which is the implicit assumption that attacks originate from isolated identities. This work systematically demonstrates that the SCA is fundamentally invalid in the presence of coordinated threat actors, such as Advanced Persistent Threats (APTs). We introduce a modular, open-source framework called CerberusAI for reproducible model-stealing research, and use it to simulate distributed attack...
论文介绍 本文指出当前AI模型提取攻击的防御策略大多依赖于“单客户端假设”，即假定攻击源自孤立身份。研究通过引入模块化开源框架CerberusAI，系统性地证明了该假设在面临高级持续性威胁等协同攻击者时是无效的，从而揭示了现有防御的重大缺陷。
第一作者: Jinghuai Zhang · 方向: 网络安全
成员推理攻击图像检索增强生成版权审计跨模态检索分布外检测
Abstract:Image-based Retrieval-Augmented Generation (IRAG) conditions a frozen generator on reference images retrieved from an external database, supporting both text-to-image (T2I) and question answering (Q&A) tasks. Because these databases are opaque and web-scraped, copyright holders need ways to audit whether specific images appear in them. While prior work employs membership inference attacks (MIAs) to audit uni-modal, text-based RAG, they fail to transfer to IRAG due to two key challenges. First, cross-modal retrieval: text-RAG MIAs force retrieval of the target passage by injecting its content into the query, which is unavailable in IRAG since images cannot be embedded into text queries; even accurate image captions fail to bridge the modality gap. Second, discriminative signal extraction: text-RAG MIAs extract membership signals by prompting the generator to answer multiple...
论文介绍 本文针对基于图像的检索增强生成（IRAG）系统，提出了一种成员推理攻击方法，旨在审计其外部数据库中是否包含特定版权图像。研究解决了从文本RAG迁移方法到图像场景的两大挑战：如何通过文本查询检索到目标图像，以及如何从生成器中提取有效的成员信号。
第一作者: Jinghuai Zhang · 方向: AI 安全
大语言模型合并供应链攻击后门攻击任务向量自回归解码
Abstract:Model merging composes specialized capabilities into a single LLM by aggregating task vectors sourced from unverified public platforms, exposing a critical supply-chain attack surface: Because any malicious behavior can be encoded into a task vector, and merging grants third-party vectors direct write access to model weights, an attacker-provided task vector can enable or amplify diverse downstream threats. Prior work studies only backdoor attacks against model merging for classifiers using static arithmetic heuristics, which fail to effectively handle diverse attacks on generative LLMs for three reasons. (i) LLMs rely on autoregressive decoding, where the minor parameter drift introduced by merging compounds across tokens and rapidly degrades the attack. (ii) Attackers have no knowledge of the victim's merging configurations, causing a static attack vector optimized in...
论文介绍 本文研究了大语言模型合并这一新兴范式中的供应链安全风险。模型合并通过聚合来自公开平台的任务向量来组合能力，但这允许攻击者注入恶意向量。论文指出，针对生成式LLM的后门攻击在自回归解码过程中面临参数漂移的挑战，并提出了优化静态攻击向量以适应不同合并配置的方法。
第一作者: Yang Yang · 方向: AI 安全
远程证明机密计算Kubernetes可信执行环境
Abstract:The rise of LLM-as-a-Service and other confidential cloud workloads demands cryptographic proof that user data is processed in a trusted, untampered environment. Existing solutions, notably Confidential Containers (CoCo), enforce a strict "one Pod per VM" model that attests only the Guest OS stack, leaving container-level identity unverified and incurring prohibitive per-VM resource overhead. We present dstack-capsule, a Kubernetes platform that enables Pod-level remote attestation on Intel TDX by allowing multiple Pods to share a single Confidential VM while each retains independent, hardware-backed proof of identity. Our key insight is a two-layer attestation architecture: static platform measurements are frozen in RTMR[3] via an irreversible privilege fuse, while dynamic Pod identities (pod_uid, pod_spec_hash, workload_id) are embedded in the TDX Quote's report_data field...
论文介绍 在LLM即服务等机密云工作负载中，现有方案强制「每个Pod对应一个虚拟机」，仅能验证Guest OS堆栈，导致容器级身份未验证且资源开销巨大。本文提出dstack-capsule平台，其核心是两层证明架构：通过Intel TDX硬件，在单个机密虚拟机内实现多个Pod的独立身份证明。静态平台测量固化于RTMR[3]，而动态Pod身份信息则嵌入TDX Quote的报告数据中，从而在保证安全性的同时降低资源成本。
第一作者: Jianwei Tai · 方向: 软件安全
大语言模型代码安全信息论安全预算
Abstract:AI programming assistants make natural-language prompts a software-development interface, so small prompt perturbations become usability and security risks. We study an information-theoretic trade-off for code LLMs between functional capacity, $\Cap=\rmI(c^*;c_\pi)$, and perturbation retention, $\Sec=\rmI(c_\pi;\tilde c_\pi)$. Here $\Sec$ is a retention-channel quantity, not a direct measure of exploit success or vulnerable-code generation. For code completion modeled as $p\to c_\pi$ with perturbed prompt $\tilde p$, we prove $\Cap+\Sec\le \rmH(c^*)+\rmI(p;\tilde p)$, decomposing the budget into task entropy and prompt leakage. A deterministic-embedding corollary gives the hidden-state version, and a tokenizer/gzip companion bound gives a model-agnostic ceiling on sequence-level task entropy. Empirically, we estimate embedded $\Cap$ and $\Sec$ from output-only last-token...
论文介绍 AI编程助手将自然语言提示作为软件开发接口，使得微小的提示扰动可能引发安全风险。本文从信息论角度研究代码大语言模型在功能容量与扰动保持之间的权衡关系。通过建立形式化模型，将安全预算分解为任务熵和提示泄露两部分，并证明了容量与安全的上界。研究为评估和管理代码生成模型的安全性提供了理论框架。
第一作者: Christophe Parisel · 方向: 系统安全
身份与访问管理权限风险云安全非人类身份
Abstract:Cloud permission governance implicitly treats permission equivalence as a static relation. We show that for non-human identities (NHIs), equivalence has two irreducible components: structural equivalence, capturing identical permission profiles at a snapshot via graph fibration, and temporal equivalence, capturing recurring permission states via strongly connected components (SCCs) in a fiber transition graph. We call the equivalence classes under temporal equivalence privilege circuits. We formalize a three-layer framework: (1) a spatial quotient of the permission graph via fibration, (2) a lineage partition organizing stable transition compartments, (3) windowed SCC analysis as a temporal quotient within lineages. Empirical evaluation on a large Azure tenant supports the framework. Backtesting demonstrates that early observation of ratchet-type privilege circuits predicts...
论文介绍 云权限治理通常将权限等价性视为静态关系。本文针对非人类身份（NHI），揭示了其权限等价性包含结构等价与时间等价两个不可约分量，并提出了一个三层形式化框架：通过纤维化构建空间商集，通过谱系划分组织稳定过渡区隔，并利用窗口化强连通分量分析实现时间商集。该框架能更精确地建模和预测NHI的权限风险演化，支持早期威胁检测。
第一作者: Biagio Montaruli · 方向: AI 安全
恶意软件检测macOS机器学习领域特征
Abstract:Despite the growing popularity of macOS among end users and enterprise systems, malware research has primarily focused on Windows and Android operating systems, leaving the problem of macOS malware detection relatively unexplored. Indeed, the specificity of the operating system and the unique characteristics of the Mach-O file format can play a fundamental role in the classification of unknown samples, drastically increasing the detection rate. In this work, for the first time in the literature, we employ new domain-specific features, i.e., static features specific to macOS binaries, such as embedded certificates, entitlements, persistence techniques and key system APIs, to train a machine learning malware detector. We perform a comprehensive experimental evaluation on a novel dataset of 41,129 samples, comprising 11,413 benign and 29,716 malicious executables, and demonstrate...
论文介绍 macOS恶意软件检测研究相对不足，但其操作系统和Mach-O文件格式的特性对分类至关重要。本文首次提出利用macOS二进制文件的领域特定静态特征，如嵌入式证书、权限、持久化技术和关键系统API，来训练机器学习检测器。通过在包含四万余样本的新型数据集上进行全面评估，证明了这些特征能显著提升恶意软件的检测率。
第一作者: Shuning Zhang · 方向: 软件安全
生成式AI电商安全网络欺诈数字证据
Abstract:E-commerce dispute resolution typically relies on the security assumption that digital evidence truthfully reflects physical reality. Generative AI (GenAI) invalidates this threat model, enabling attackers to fabricate hyper-realistic evidence of product defects at negligible cost. Through semi-structured interviews with merchants (N=17) and platform workers (N=13) in the Chinese e-commerce market, we characterize this shift toward GenAI-enabled scalable fabrication. We outline a taxonomy of four GenAI-enabled threat vectors across the transaction, dispute, logistics and communication phases, highlighting how attackers exploit GenAI to synthesize physically plausible product defects at scale. To mitigate these threats, platforms and merchants are adapting verification strategies, relying on AI tools for automated screening and adversarial interrogation (e.g., requesting...
论文介绍 电商平台纠纷解决依赖数字证据真实反映物理现实的假设，但生成式AI（GenAI）使得攻击者能以极低成本伪造超现实的产品缺陷证据。本文通过对商家和平台工作者的访谈，刻画了GenAI驱动的规模化伪造威胁，并梳理出涵盖交易、纠纷、物流和沟通四个阶段的威胁向量分类法。同时，探讨了平台与商家正在采用的AI筛查和对抗性询问等缓解策略。
第一作者: Daehyun Jang · 方向: 密码学协议
全同态加密隐私保护嵌入查询效率优化
Abstract:Many NLP or recommendation models begin by mapping discrete client inputs to embedding vectors. Since inputs can reveal sensitive information, the embedding step must be protected in privacy-preserving inference. Fully Homomorphic Encryption (FHE) enables inference over encrypted client data, but turns embedding lookup from simple table access into homomorphic computation. To keep the embedding table server-side and avoid transmitting encrypted embedding vectors from the client, we focus on server-side lookup: the client sends only a small encrypted index. Prior ICML 2024 work first builds a one-hot vector from the encrypted index before multiplying with the embedding table, and this one-hot generation is the dominant cost. One-hot-based methods are expensive in FHE: they construct a p-dimensional selection vector via an equality test for each coordinate, requiring $O(p \log...
论文介绍 在隐私保护推理中，使用全同态加密（FHE）处理客户端加密数据时，嵌入查找会从简单的表访问变为复杂的同态计算。为在服务器端完成查找并避免传输加密嵌入向量，本文聚焦于服务器端查找方案，客户端仅需发送加密索引。针对先前方法中生成独热向量计算成本高的问题，本文提出了基于加密紧凑查询的新方法，显著提升了隐私保护嵌入查询的效率。
第一作者: Muberra Ozmen · 方向: AI 安全
大语言模型安全对抗对话几何分析越狱攻击
Abstract:Multi-turn jailbreak attacks on large language models (LLMs) reveal a mismatch in current guardrails: they operate on individual turns, while attacks unfold as trajectories across conversations. We propose a shift from content to dynamics, modeling conversations as paths in representation space and asking whether adversarial intent is encoded early in their geometry. We introduce PsychoPass, a framework that extracts geometric features from conversation trajectories in embedding space to predict a potential attack before harmful content is produced. These features achieve near-perfect performance in naïve classifiers, which is largely explained by the inclusion of number of turns as a feature. After removing this confound, a smaller but consistent geometric signal remains, with classification performance that does not depend meaningfully on encoder choice. Crucially, this...
论文介绍 多轮越狱攻击揭示了现有防护措施的不匹配：它们作用于单轮对话，而攻击以跨对话轨迹展开。本文提出从内容分析转向动态分析，将对话建模为表示空间中的路径，并引入PsychoPass框架，通过提取对话轨迹的几何特征来预测潜在攻击。即使在移除对话轮数等混杂因素后，仍能检测到一致的几何信号，表明对抗性意图在早期几何特征中就有编码。
第一作者: Bagus Rakadyanto Oktavianto Putra · 方向: AI 安全
智能合约安全大语言模型代码审计模型轻量化
Abstract:Smart contracts face critical security challenges that require thorough auditing in decentralized web services. While Large Language Models (LLMs) have shown promise in automated vulnerability detection, existing approaches lack severity evaluations with actionable remediation and demand unnecessarily massive computational overhead. In this study, we introduce an efficient end-to-end smart contract security audit framework utilizing lightweight, highly optimized open-source LLMs (0.6B-4B parameters). Our framework decouples comprehensive audit tasks into four interconnected components: vulnerability detection, explanation, severity classification, and remediation recommendation. To maintain high accuracy without massive parameters, we implement Rank-Stabilized Low-Rank Adapters (rsLoRA), knowledge distillation, and a custom Chain-of-Verification (CoVe) aggregation strategy to...
论文介绍 智能合约安全审计需求迫切，但现有基于大语言模型的方法缺乏严重性评估与可操作修复建议，且计算开销过大。本文提出一个高效的端到端审计框架，利用参数量较小（0.6B-4B）的开源LLM。框架将审计任务解耦为漏洞检测、解释、严重性分类和修复建议四个组件，并通过低秩适配器、知识蒸馏和自定义聚合策略在不依赖巨大参数量的情况下保持高精度。
第一作者: Hang Li · 方向: AI 安全
提示注入攻击大语言模型自动评分系统安全威胁教育评估
Abstract:The emergence of large language models (LLMs) has significantly accelerated recent research on LLM-based automatic grading (AG) systems. Benefiting from the strong instruction-following capabilities and broad prior knowledge of LLMs, educators can deploy AG systems across diverse tasks using only natural language rubrics while achieving satisfactory grading performance. Despite these advantages, new security concerns may also arise. In particular, prompt injection (PI) attacks have recently become a major threat to LLM-based applications. In the context of AG, attackers can potentially exploit PI vulnerabilities to manipulate grading systems into assigning artificially high scores regardless of the actual answer quality. Such behavior poses serious risks to the fairness, reliability, and integrity of educational assessment. In this work, we study PI attacks in AG systems, and...
论文介绍 研究基于大语言模型的自动评分系统中的提示注入攻击风险。攻击者可利用漏洞操纵系统分配高分，威胁教育评估的公平性和完整性。本文探索攻击方法，强调需增强安全机制以应对潜在威胁。
第一作者: Shidong Pan · 方向: AI 安全
权限框架代理技能大语言模型代理安全治理运行时控制
Abstract:Agent skills extend LLM agents with reusable instructions, scripts, tool bindings, and contextual dependencies. However, current skill ecosystems largely rely on trust-based loading and static inspection, leaving a gap between what a skill can inject into an agent's context and what it can cause the agent to do at runtime. This gap introduces new security and privacy risks, and existing defenses primarily inspect skill files statically or regulate individual tool calls, without systematically connecting a skill's declared intent with its runtime behavior. In this paper, we present SkillGuard, a skill-centric permission framework that treats skills as permission-bearing executable artifacts. SkillGuard introduces a dual-plane governance model that jointly regulates context influence and action side effects through skill manifests, runtime access control, user-mediated...
论文介绍 针对LLM代理中技能加载和运行时行为的安全风险，提出SkillGuard权限框架。该框架通过技能清单和运行时访问控制，联合监管上下文影响和动作副作用，以增强代理系统的安全性和隐私保护。
第一作者: Bowen Xue · 方向: 密码学协议
以太坊L2替代数据可用性安全集成验证框架共识机制
Abstract:Alternative data availability (AltDA) systems provide Ethereum L2s with an external data publication layer for high throughput rollup designs. By moving bulk data publication outside of Ethereum, AltDA allows L2s to process more data than native DA. However, this replacement introduces a new consensus critical integration layer. Existing ecosystem frameworks identify high level risks, such as external DA trust assumptions and the presence or absence of a DA verifier, but do not provide a complete specification for how an L2 should integrate with AltDA. This gap can lead to L2 halts, inconsistent derivation across honest L2 nodes, invalid state assertions, or bridge attacks. This paper presents a canonical validation framework for secure AltDA integration. We model the boundary as a typed, deterministic, and total translation from L1 inbox bytes to an AltDA commitment, then to...
论文介绍 研究以太坊L2与替代数据可用性系统集成的安全问题。现有框架缺乏完整规范，可能导致L2停机或桥攻击。本文提出端到端验证框架，模型化边界转换以确保安全集成和数据一致性。
第一作者: Anjun Gao · 方向: 软件安全
后门攻击大语言模型后修复框架安全防御梯度分析
Abstract:Large language models remain vulnerable to jailbreak backdoor attacks, where adversaries poison safety alignment data to embed hidden triggers that bypass safety mechanisms. Existing defenses often require comprehensive attack information or multiple triggered examples, making them impractical when defenders only observe a single reported failure case without knowing whether it stems from a backdoor attack or a natural alignment bug. This paper presents Patcher, a post-hoc defense framework that repairs backdoored language models using only a single reported failure case and the model parameters. Patcher operates in two stages. First, it localizes backdoor triggers by computing response-conditioned gradient-based saliency scores and applying adaptive clustering to separate triggers from benign context. Second, it patches the model through a constrained fine-tuning objective...
论文介绍 针对大语言模型中的后门攻击，提出Patcher后修复防御框架。该框架仅需单个失败案例和模型参数，通过梯度分析定位触发器并约束微调修复模型，无需完整攻击信息，提升实用性。
第一作者: Hina Dixit · 方向: 系统安全
隐私边界语言模型适应聚合更新审计架构系统安全
Abstract:Cross-organization language-model adaptation increasingly faces hard governance constraints: in many deployments, device-level model state-parameters, activations, optimizer state, and per-device updates-cannot be exported outside an administrative boundary. Existing distributed and federated stacks typically assume cross-site model exchange and then retrofit privacy mechanisms, which complicates compliance and makes auditing brittle. We present Echelon, a boundary-first training architecture that enforces device-level model-state non-export as a systems invariant. Devices train locally inside each boundary; the only cross-boundary payloads are securely aggregated boundary-level deltas plus O(1) coordination metadata, exposed through a concrete audit surface. Restricting exchange to aggregates changes the optimization problem: the system must remain stable under WAN delay...
论文介绍 解决跨组织语言模型适应中的隐私治理约束。提出Echelon边界优先训练架构，强制设备级模型状态不导出，仅交换聚合增量。这改变优化问题，增强合规性和审计性，适用于分散式部署。
第一作者: Faruk Alpay · 方向: 系统安全
侧信道泄漏计量发布统计分析隐私审计安全量化
Abstract:Public scientific and metrology releases can leak the hidden settings that produced them. We formalize and quantify this risk as a profiled statistical side-channel audit: a release map exposes finite-band statistics of a power spectral density (PSD), a profiled observer trains labeled template spectra under an explicit budget, and a challenge release is drawn from one of two utility-equivalent recipes separated by a protected coordinate. Averaged PSD bins follow a gamma channel, replaced by a covariance-weighted log-spectrum channel when the bins are correlated; this yields exact Kullback-Leibler divergences, Chernoff exponents, protected-bit advantage bounds, and finite-training, finite-library, finite-compute, and model-mismatch corrections. Our headline result is a finite-band transport-leakage law: after amplitude and blur are eliminated, the protected acid-transport...
论文介绍 量化公共科学和计量发布中的侧信道泄漏风险。形式化统计模型，分析功率谱密度数据，推导泄漏界限。本文提供有限带宽传输泄漏定律，帮助评估发布数据的隐私保护效果。
第一作者: Goda Cicėnaitė · 方向: 安全研究
人为因素网络安全中小企业安全挑战意识培训
Abstract:Cybersecurity threats are increasing in all aspects of society due to the integration of digital systems into modern-day life and a volatile geo-political landscape. Technical factors are an ongoing arms race; however, the threat surface from human and social factors is still present, often providing malicious actors the means to bypass complex technical security controls. Understanding human factors in light of technical evolution is essential to ensure security controls remain effective. This study presents the results of a survey on cybersecurity challenges within public and private sector organisations, including critical infrastructure providers, in Iceland (N = 130). From the management perspective, human factors were strongly noted as challenges and barriers to their organisations' security. These challenges include a lack of adequate training or awareness, hiring...
论文介绍 通过调查研究冰岛公私部门网络安全中的人为因素挑战。结果显示管理视角下，缺乏培训和意识是主要障碍。本文强调在技术演进中需重视人为因素，以确保安全控制的有效性。
第一作者: Florian Störtz · 方向: 软件安全
字节模型大语言模型恶意软件分析编译代码安全检测
Abstract:Malware analysis starts with the raw bytes of an executable program, and tools to "lift" these to higher-level representations, such as assembly, are expensive and subject to error. Large Language Models (LLMs) cannot process raw byte representations and answer questions about them. To this end, we present the first byte-native LLM. Based on a vocabulary expansion technique using a bespoke byte tokenizer, such a model is capable of responding to complex questions about malware binaries, with accuracies ranging from 69% for malware family classification to 98% for architecture classification. Our findings indicate that providing domain knowledge during training is essential for this application -- off-the-shelf models lack both accuracy and insight. We've deployed this emerging solution to a limited number of analysts to gather feedback for further improvements.
论文介绍 提出首个字节原生大语言模型，用于分析恶意软件二进制文件。基于定制字节分词器，模型能回答复杂问题，如恶意软件家族分类。提供域知识训练至关重要，现部署于分析师以收集反馈改进。
第一作者: Alexandre Cristovão Maiorano · 方向: 密码学协议
LLM安全威胁归因OWASP-LLM-Top-10防御归因对抗性攻击
Abstract:Production LLM applications stack several defense families -- refusal-phrase filters, token-budget controls, model allowlists, rate limits, tool-registry authentication -- yet existing breach-and-attack-simulation (BAS) benchmarks report a single aggregate coverage number, hiding which family closes which threat. We measure attribution. We add four OWASP-LLM-Top-10-aware agents to a 21-agent baseline scanner and target a lattice of four synthetic LLM endpoints: $L_0$ (no defenses), $L_1$ (refusal-only), $L_2$ (budget-only), and $L_3$ (full stack). $L_1$ and $L_2$ are sibling single-axis ablations, not subsets of each other; $L_3$ is their union plus tool-registry authentication and credential scrubbing. Across $N=10$ replications, the per-OWASP finding count is clean: refusal alone removes all LLM01 (jailbreak) and LLM07 (system-prompt leakage) findings; budget alone removes...
论文介绍 本文针对现有LLM安全基准仅报告单一覆盖率数字、无法揭示具体防御措施对应何种威胁的问题，提出了一种威胁归因方法。研究构建了包含四类防御配置（无防御、仅拒绝、仅预算、全栈）的合成LLM端点网格，并部署增强的代理扫描器进行测试。实验系统性地量化了拒绝短语过滤器、令牌预算控制等不同防御家族对OWASP-LLM-Top-10中各项威胁（如越狱、系统提示泄露）的覆盖效果，为理解防御机制的有效性与局限性提供了细粒度视角。
第一作者: Abu Taib Mohammed Shahjahan · 方向: AI 安全
深度伪造检测对抗性鲁棒性频域统计建模泛化能力AI安全
Abstract:The rapid advancement of Generative AI has introduced remarkable opportunities while simultaneously raising critical concerns regarding content authenticity. While recent work has increasingly focused on improving the generalization of deepfake detectors across unseen generative models, their robustness against adversarial attacks remains limited. In particular, Abdullah et al. (IEEE SP 2024) evaluated eight detectors and demonstrated that most of them exhibit significant performance degradation under adversarial attacks. We also observed the same phenomenon by testing seven most recent state-of-the-art detectors. To address this problem, we propose a unified framework that integrates three complementary design principles without relying on adversarial training data: (i) higher-order statistical modeling in the frequency domain via Discrete Cosine Transform (DCT)-based moment...
论文介绍 生成式AI的进步使深度伪造检测面临严峻的对抗性攻击挑战，现有检测器在攻击下性能显著下降。本文旨在提升检测器的鲁棒性，提出了一种不依赖对抗性训练数据的统一框架。该框架整合了三个互补原则：基于离散余弦变换的频域高阶统计建模、一种新颖的自适应损失函数以及特征空间正则化。研究评估了多个最新检测器，并在面对对抗性攻击时观察到明显性能差距，所提框架旨在增强其抵抗攻击的能力，从而提高检测器在真实世界应用中的可靠性。
第一作者: Eden Yavin · 方向: 系统安全
身份安全态势管理跨供应商基准多跳实体解析代理AI评估云安全
Abstract:The rapid proliferation of multi-cloud and SaaS platforms has transformed Identity Security Posture Management (ISPM) into a fundamentally cross-vendor challenge: critical misconfigurations and privilege escalation paths increasingly span multiple identity providers, infrastructure layers, and authentication systems never designed to interoperate. Existing evaluations focus on isolated single-platform environments and provide no means to assess whether an AI agent can reason across these fragmented boundaries. To address this gap, we introduce the Cross-Vendor Sola ISPM Benchmark, a production-grade benchmark of 50 data-grounded tasks requiring multi-hop entity resolution and cross-system correlation across eight integrated enterprise platforms including AWS, Okta, Azure AD, and Google Workspace. We also contribute an evaluation framework measuring not only final answer...
论文介绍 随着多云和SaaS平台的普及，身份安全态势管理已成为跨供应商的核心挑战，现有评估局限于单一平台环境。本文提出了跨供应商Sola ISPM基准，这是一个包含50个生产级任务的基准测试，这些任务要求跨八个集成企业平台（如AWS、Okta、Azure AD）进行多跳实体解析和跨系统关联。该工作不仅提供了一个评估AI代理在碎片化身份生态系统中推理能力的平台，还贡献了一个评估框架，用于衡量代理在多供应商安全推理任务中的最终答案准确性和推理过程质量。
第一作者: Xiaoqi Weng · 方向: AI 安全
AI代理同意完整性人机协同审批可信路径安全关键操作
Abstract:Coding agents gate consequential actions behind a human-in-the-loop approval dialog, but the dialog is narrated by the agent itself: the human approves a summary the agent writes. The Lies-in-the-Loop (LITL) attack shows that summary is forgeable, so a compromised agent can show a benign description while a different action runs. This paper names the missing property, Consent Integrity, by importing What You See Is What You Sign (WYSIWYS) and the trusted-path property into the agent approval channel: the action shown to the human must be rendered by a trusted mediator from the real action at the boundary, not the agent's narration, over a path the agent cannot spoof, and bound to the exact action that executes. Two twists distinguish it from classical WYSIWYS: the renderer is the adversary, and the boundary ground truth is a low-level event that must be decoded without...
论文介绍 在人机协同的LLM代理中，代理负责叙述需要人类批准的操作，但「环路中的谎言」攻击表明叙述可能被伪造，导致人类批准的内容与实际执行内容不符。本文定义了「同意完整性」这一缺失属性，借鉴「所见即所签」和可信路径思想，要求呈现给用户的操作必须由可信中介从底层真实操作中渲染，且通过代理无法伪造的路径传达，并与执行操作严格绑定。该研究为构建可安全批准关键操作的AI代理提供了重要的安全属性框架和防御思路。
第一作者: Eliot Krzysztof Jones · 方向: AI 安全
网络安全AI代理拒绝边界风险评估攻击性安全
Abstract:Agentic scaffolds have dramatically improved LLM performance on complex, long-horizon tasks, yielding both broad benefits and amplified risks in domains like cybersecurity. Existing benchmarks for AI agents in cybersecurity focus mainly on measuring proficiency--how effectively agents can complete offensive security tasks--but neglect a critical question: when and how should agents refuse harmful requests? We present the first framework for establishing refusal boundaries in offensive security contexts. Our framework defines (1) principled criteria for when tasks should be refused, (2) categories of tasks that warrant refusal, and (3) evaluation methodology for measuring agent robustness under both benign and adversarial conditions. We apply this framework to assess how current LLM-powered agents adhere to appropriate refusal boundaries across a range of web-based offensive...
论文介绍 现有评估AI代理在网络安全中能力的基准主要关注代理完成攻击任务的效能，而忽略了代理何时以及如何拒绝有害请求这一关键问题。本文首次提出了一个用于在攻击性安全上下文中建立拒绝边界的框架。该框架定义了任务应被拒绝的原则性标准、需要拒绝的任务类别，以及评估代理在良性及对抗性条件下遵循拒绝边界稳健性的方法。研究应用此框架评估了当前LLM代理在多种基于Web的攻击任务中的拒绝行为，为安全地部署网络安全AI代理提供了评估准则。
第一作者: Chengliang Liu · 方向: AI 安全
RAG系统推理成本攻击知识库投毒资源耗尽安全漏洞
Abstract:Retrieval-Augmented Generation (RAG)-enhanced LLM systems, while powerful, introduce substantial inference costs due to the inclusion of an extra multi-stage pipeline that dynamically retrieves and synthesizes information from external knowledge sources. This high operational cost exposes a critical vulnerability to Inference Cost Attacks (ICAs). However, existing ICAs often rely on the impractical assumption of direct prompt manipulation. We argue that a more feasible and potent threat to RAG-enhanced LLM systems arises from poisoning external knowledge bases (e.g., web knowledge from the Internet). In this work, we introduce the Retrieval-Augmented Inference Cost Attack (RA-ICA), a novel attacking paradigm that targets the computational cost of RAG-enhanced LLM systems by injecting malicious documents into external knowledge corpus. To operationalize this attack, we propose...
论文介绍 检索增强生成系统因其动态检索外部知识的流程而产生较高推理成本，这使其易受推理成本攻击。现有攻击常依赖不切实际的直接提示操作假设，本文认为通过投毒外部知识库是一种更可行且有效的威胁。研究提出了一种新颖的攻击范式——检索增强推理成本攻击，其通过向外部知识语料库中注入恶意文档来攻击RAG系统的计算成本。该工作揭示了RAG系统在知识源层面的新安全漏洞，并分析了攻击机理与潜在防御方向。
第一作者: Huanli Gong · 方向: AI 安全
多轮越狱攻击语义保持输出重写反馈信号干扰LLM安全防御对抗性攻击
Abstract:Multi-turn jailbreak attacks pose a growing threat to large language model (LLM) safety because they exploit feedback from auxiliary judge models to iteratively refine prompts toward harmful goals. Existing defenses largely detect or block unsafe content at individual turns or at the final response, leaving the judge-driven refinement loop intact and allowing attackers to extract informative feedback from intermediate interactions. We introduce D-Judge, a semantics-preserving output rewriting defense that intervenes directly in this loop by rewriting the victim LLM's responses before they are evaluated by the attacker's judge. By misaligning the judge's feedback signal without changing the meaning of the original response, D-Judge derails the attacker's prompt-refinement process, causing subsequent queries to be optimized against a distorted signal of attack progress. To...
论文介绍 多轮越狱攻击利用辅助评估模型的反馈迭代优化提示以达到有害目标，现有防御多在单轮或最终响应阶段进行拦截，未能破坏攻击者的反馈优化循环。本文提出D-Judge防御方法，通过直接干预该循环，在攻击者的评估模型接收前，对受害者LLM的响应进行语义保持的输出重写。此操作旨在误导攻击者的反馈信号而不改变原始响应的含义，从而扰乱其提示优化进程。该方法为防御依赖反馈驱动的复杂越狱攻击提供了一种新思路。
第一作者: Anushka Sheoran · 方向: AI 安全
医疗AI安全多轮越狱攻击对抗性评估安全基准聊天机器人
Abstract:Patient-facing medical chatbots are commonly evaluated on single-turn prompts, yet real users push back after refusals, add urgency, and invoke authority. We introduce MultiTurnPSB, a four-turn adversarial extension of PatientSafetyBench, and evaluate GPT-4.1-mini under fixed template, template-adaptive, and live adversarial attacks. Unsafe responses rise from 35% to nearly 80% by Turn 4 under live attack. Under the same adversary, GPT-4.1-mini and Claude Sonnet 4.5 are statistically indistinguishable at baseline but diverge to a 19x gap by Turn 4, a difference invisible to single-turn evaluation. We characterize four degradation trajectory signatures and identify a two-element attack formula responsible for most catastrophic failures. A lightweight input-side classifier reduces Turn 4 unsafe responses by 52 percentage points despite severe accuracy degradation, but the 45%...
论文介绍 面向患者的医疗聊天机器人通常在单轮提示下评估，但真实用户常在被拒绝后坚持追问、添加紧迫性或援引权威。本文引入MultiTurnPSB，一个包含四轮对抗性对话的扩展基准，用于评估医疗AI的安全性。研究在多种攻击策略下测试了模型，发现不安全响应率随对话轮次增加而显著上升，且单轮评估无法揭示不同模型在持续攻击下的安全差异。该工作揭示了多轮交互带来的真实风险，并评估了基于分类器的输入端防御效果，为医疗对话AI的安全评估提供了更贴近现实的框架。
第一作者: Yingqi Zhang · 方向: 软件安全
LLM代理运行时系统库操作系统能力控制长期运行
Abstract:Large language model (LLM) agents are evolving from request-response assistants into long-running software actors: they maintain state across model calls, fork subtasks, wait for external events, request human authority, generate tools, and perform side effects that must be resumed and audited. This paper presents Agent libOS, a library-OS-inspired runtime substrate for LLM agents. Agent libOS runs above a conventional host operating system; it does not implement hardware drivers, kernel-mode isolation, or a POSIX-compatible operating system. Instead, it treats an agent as an AgentProcess: a schedulable execution subject with process identity, parent-child lineage, lifecycle state, a tool table derived from an AgentImage, typed Object Memory, explicit capabilities, human queues, checkpoints, events, and audit records. Its central design rule is tools are libc-like wrappers...
论文介绍 大型语言模型代理正从请求-响应助手演变为长期运行的软件实体，需要跨调用维护状态、分派子任务和处理外部事件。本文提出Agent libOS，一种库操作系统启发的运行时基板，将代理视为可调度进程，提供进程身份、生命周期状态、工具表、对象内存、显式能力等机制，支持工具生成、检查点和审计，以治理复杂代理行为。
第一作者: Vedant Jawandhia · 方向: 安全研究
机器遗忘持续学习梯度投影表示擦除
Abstract:We propose PURGE, a machine unlearning algorithm built on a simple but an under-exploited observation: continual learning (CL) and machine unlearning (MU) which are fundamentally dual problems. CL tries to learn new tasks without forgetting old ones; MU tries to erase specific data without hurting retained performance representing the same underlying tension in opposite directions. PURGE leverages this duality by adapting gradient projection from A-GEM (Chaudhry et al., 2019) so that every unlearning step is constrained to not increase the retain-set loss. On top of this, it performs multi-layer representation erasure, pushing forget-set activations in intermediate layers towards the retain distribution to remove information from hidden representations rather than just suppressing it at the output. A key design choice is the retain-confusion target: rather than pushing forget...
论文介绍 机器遗忘旨在从模型中擦除特定数据而不影响保留性能，与持续学习形成对偶问题。本文提出PURGE算法，利用梯度投影约束遗忘步骤以保持保留集损失，并通过多层表示擦除从隐藏层移除信息，从而提升隐私保护和模型编辑的效率。
第一作者: Alex Leung · 方向: AI 安全
AI损失保险索赔CER框架状态重建残余风险转移
Abstract:AI losses that arise through an insured organization's generative or agentic AI system require state reconstruction, not merely event reconstruction, because the relevant state changes as the system reasons, retrieves, calls tools, and acts. The relevant question is not only what loss occurred, but what the system was allowed to do, what it actually did, and whether that reconstructed loss can support insurance claim recovery. This paper addresses losses in which the insured's AI system is in the causal chain, including externally triggered failures such as prompt injection, retrieval-augmented generation (RAG) poisoning, malicious tool output, credential misuse, and data poisoning. Specifically, this paper introduces CER, a use-case-level diagnostic for AI residual risk transfer. C (control boundary) asks whether the system had an enforceable operating envelope. E (evidence...
论文介绍 AI系统引起的损失需状态重建以支持保险索赔，而非仅事件重建。本文引入CER诊断框架，通过分析控制边界、证据和重建，评估AI残余风险转移，适用于提示注入、数据中毒等场景，为保险理赔提供依据。
第一作者: Zehra Karadağ · 方向: 系统安全
硬件逆向工程教育课程供应链安全数字电路分析
Abstract:Integrated Circuits (ICs) are omnipresent, yet their globalized manufacturing process remains vulnerable to supply chain threats. Hardware Reverse Engineering (HRE) is essential for detecting such threats and re-establishing trust; however domain experts remain scarce due to a lack of educational programs. To contribute educational insights in this critical and rapidly evolving technology domain, we present our HRE course focusing on digital circuit analysis and digital circuit extraction from ICs. The course targets junior-level undergraduates at a major European research university. The curriculum has been refined over nine iterations (2017-2025), with several alumni subsequently pursuing careers in the HRE field. By reflecting on the evolution of the course organization, content, and assignments, we derive key lessons learned. We further distill these insights into...
论文介绍 硬件逆向工程对检测供应链威胁至关重要，但教育项目稀缺。本文基于八年教学经验，设计面向本科生的课程，涵盖数字电路分析和提取，通过多次迭代优化课程内容，分享关键教训，以培养领域专业人才。
第一作者: Amjad Ibrahim · 方向: 软件安全
代理AI授权框架委托范围动态治理
Abstract:As AI systems evolve from passive models into autonomous active agents capable of initiating actions, collaborating, and delegating tasks, the traditional boundaries of software systems blur. Traditional authorization and delegation frameworks, built around fixed principals, explicit requests, and static scopes, are insufficient to govern agentic systems. Agentic AI demands richer authorization semantics: agents must inherit and delegate permissions, act under time-limited authority, and coordinate through shared protocols. Existing Identity and Access Management (IAM) systems fail to fully capture this notion of agency, lacking mechanisms for recursive delegation, contextual boundaries, and dynamic scoping as executable governance primitives. Unlike access delegation standards such as OAuth 2.0, we treat delegation as a contractual term rather than merely a static token-based...
论文介绍 代理AI系统需丰富授权语义，传统框架不足。本文提出组合授权框架，支持递归委托、上下文边界和动态范围作为治理原语，将委托视为契约条款而非静态令牌，以管理代理间的权限继承和协作。
第一作者: Farhan Sheth · 方向: 密码学协议
隐私保护临床部署令牌级加密选择性编辑
Abstract:While large language models (LLMs) are increasingly used for clinical applications, many existing pipelines require sending raw sensitive health information to remote servers for processing, which heightens the risk of privacy leakage. A natural approach to mitigate this risk is to encrypt the data before transmission. However, straightforward solutions such as encrypting the entire dataset introduce prohibitive computational, alignment, and communication overheads, rendering large-scale practical deployment infeasible. To preserve privacy while maintaining usability, we present Healthcare Encryption & Redaction via Adaptive Linguistic Decomposition (HERALD), a token-level cryptographic redaction framework designed to achieve this balance by encrypting only sensitive tokens while preserving the surrounding context for downstream model utility. HERALD combines medical...
论文介绍 LLM临床应用中，发送原始健康信息带来隐私风险。本文提出HERALD框架，通过令牌级加密选择性编辑敏感令牌，保留上下文以支持模型效用，结合医疗知识和加密技术，平衡隐私保护与可用性。
第一作者: Gurvan Richardeau · 方向: 软件安全
实例指纹LLM配置监管合规伪随机序列
Abstract:Literature reveals that a Large Language Model's (LLM) behavior is not only conditioned by its original weights but also its instance-level parameters, such as instructional prompt, sampling configuration or quantization. A model that generates safe outputs under one configuration may produce toxic content under another. However, current LLM identification techniques (such as fingerprinting) focus on intellectual property protection, and their design favors robustness to changes in these instance-level parameters. This poses a critical challenge for AI regulation in which compliance assessments target actual deployed behaviors, not model provenance. In this paper, we introduce instance-level fingerprinting, a regulator-oriented paradigm that distinguishes configurations of the same LLM. Our method FLIPS, exploits biases in generated binary random sequences to reach 96%...
论文介绍 LLM行为受实例参数影响，现有指纹技术侧重知识产权保护。本文引入实例级指纹概念，针对监管需求区分相同模型的不同配置，利用生成的二进制随机序列偏置，达到高识别率，支持合规评估。
第一作者: Adiwena Putra · 方向: 密码学协议
零知识证明加速框架软件硬件协同设计可扩展性
Abstract:Zero-knowledge proofs (ZKP) allows a prover to convince a verifier of computational correctness without revealing private data, ensuring both privacy and verifiability. However, proof generation is highly compute-intensive, dominated by polynomial (POLY) and elliptic-curve (EC) operations. These workloads pose two key challenges for hardware acceleration: (1) efficiently supporting diverse large-precision modular multiplications, and (2) maintaining high utilization across workloads that dynamically shift between POLY and EC stages. Existing reconfigurable accelerators address these issues only partially, remaining limited in precision scalability, algorithmic flexibility, and resource efficiency. To overcome these limitations, we propose ZK-Flex, a flexible and scalable software-hardware co-designed framework for accelerating ZKP proof generation. The software layer...
论文介绍 零知识证明生成计算密集，涉及多项式和椭圆曲线操作。本文提出ZK-Flex框架，结合软件和硬件协同设计，灵活支持多样大精度模乘和动态工作负载，提高加速效率和资源利用率，促进隐私保护应用。
第一作者: Ryle Goehausen · 方向: AI 安全
LLM 安全基准评估提示注入越狱检测交叉验证
Abstract:Published evaluations of prompt-injection and jailbreak detectors for Large Language Models often suffer from two systematic weaknesses: per-dataset threshold tuning and undisclosed operating points. We describe an evaluation harness that addresses both. The detector under evaluation is scored across 16 public benchmarks (12,111 samples) using 5-fold cross-validation. StratifiedKFold (by row) is the headline pass; a parallel StratifiedGroupKFold pass over a composite key (parent-prompt id plus MinHash + LSH near-duplicate clusters at Jaccard $\gtrsim 0.8$) runs alongside it as a leakage-premium diagnostic. A single global operating point is selected on the held-out folds (max F1 subject to FPR $\leq 1\%$) and applied uniformly to every dataset, so per-dataset results reflect one threshold rather than per-benchmark optimisation. Generalisation is examined through a battery of...
论文介绍 该研究针对大语言模型的提示注入与越狱检测器评估存在的系统性弱点，提出了一种新的评估方法。该方法通过跨多个基准进行交叉验证，并设定单一全局操作点（如在FPR≤1%下取最大F1），避免了针对单一数据集进行阈值优化的偏差，从而更公正地评估检测器的泛化能力。
第一作者: Yiran Qiao · 方向: AI 安全
OOD 偏移因果解耦风险评估对抗鲁棒性直播
Abstract:Live streaming has emerged as a primary medium for social interaction and digital commerce, yet it is increasingly plagued by sophisticated risks. A fundamental challenge in this domain is \emph{tactical out-of-distribution (OOD) shift}: while malicious actors maintain stable underlying objectives, they continuously redesign narrative packaging to evade detection. Such adversarial shifts expose critical limitations of existing OOD generalization paradigms, whose assumptions are difficult to satisfy in the presence of tightly coupled intent-tactic evolution and ill-defined raw-level counterfactuals. In this paper, we tackle this issue from a \emph{latent causal} perspective and propose \underline{L}atent-\underline{P}redictive \underline{C}ounterfactual \underline{D}ecoupling~(LPCD), a plug-in framework for robust live streaming risk assessment. LPCD enables counterfactual...
论文介绍 本文关注直播风险评估中的战术性分布外（OOD）偏移挑战，即恶意行为者不断变换叙事包装以规避检测。研究从潜在因果视角出发，提出了一个名为LPCD的插件式框架，通过潜在预测反事实解耦来分离意图与策略，旨在提升风险评估模型面对此类对抗性变化的鲁棒性。
第一作者: David Turtora Zagardo · 方向: 隐私保护
表格数据合成隐私保护扩散模型几何监督数据增强
Abstract:Tabular synthesis is critical for privacy-preserving sharing and augmentation, yet diffusion models rely on implicit mechanisms to capture inter-column relationships. We introduce Geometry-Aware Tabular Diffusion (GATD), which augments tabular diffusion denoisers with pairwise angles and lengths computed from column value differences and used as inputs and auxiliary targets. Our MLP instantiation achieves state-of-the-art benchmark performance while using 3.5x fewer parameters on average (up to 25x for classification tasks): on ten datasets, it wins 8/10 Shape, 7/10 Trend, and 9/10 downstream utility (F1/RMSE), reducing Shape and Trend error by 27% and 20%. Default loss weights transfer to GNN and Transformer denoisers, improving Shape on 27/30 and Trend on 25/30 architecture-dataset cells. A matched ablation shows supervision (not extra inputs or capacity) drives the gain...
论文介绍 该论文提出了一种名为GATD的几何感知表格扩散模型，用于隐私保护的数据合成。其核心是将列间数值差异计算的成对角度与长度作为监督信号，输入并指导去噪网络学习。实验表明，该方法能以更少的参数显著提升合成数据的形状、趋势保持度和下游任务效用。
第一作者: Md Fahimul Kabir Chowdhury · 方向: AI 安全
脑机接口对抗攻击鲁棒性卷积神经网络EEG
Abstract:The development of brain-computer interfaces (BCIs) based on electroencephalograms (EEGs) has advanced significantly mainly to machine learning. Although the majority of earlier research has been on increasing classification accuracy, relatively little focus has been placed on security and robustness. According to recent research, EEG-based BCIs are susceptible to adversarial attacks, which can cause misdiagnosis due to minute, well-crafted disturbances. Evaluating model robustness against such perturbations is therefore critical for ensuring reliable deployment. In this study, we propose a lightweight custom Convolutional Neural Network (CNN) architecture to investigate adversarial robustness in EEG-based BCIs. The suggested method is assessed using two EEG datasets and contrasted with three novel CNN models tailored to EEG, namely EEGNet, DeepConvNet, and SleepEEGNet, under...
论文介绍 本文研究基于脑电图（EEG）的脑机接口（BCI）系统的安全性问题。研究设计了一个轻量级卷积神经网络架构，系统评估了BCI模型在面对对抗性攻击时的鲁棒性，并通过与多种专用EEG模型的对比，强调了在提升分类精度的同时，确保模型安全可靠部署的重要性。
第一作者: Roohan Ahmed Khan · 方向: 导航与运动 · 来源: cs.RO
强化学习自主导航奖励函数设计无人机多模态 GPT
Abstract:Deep reinforcement learning has shown strong potential for enabling autonomous robots to learn complex navigational tasks. However, its practical use still depends heavily on human designed reward functions and repeated manual fine tuning, which is time consuming and does not guarantee high success in the desired task. This paper presents AgenticRL, agent guided reinforcement learning framework that increases autonomy in reward design, policy refinement, and real world deployment for unmanned aerial vehicles (UAV) navigation tasks. AgenticRL uses a multimodal generative pre-trained tansformer (GPT) agent to interpret task information and visual scene observations, generate task specific reward functions, train policies using Proximal Policy Optimization (PPO) algorithm, and then act as a critic by evaluating the trained policy through diagnosis packets to generate feedback...
论文介绍 针对深度强化学习在机器人导航中依赖人工设计奖励函数的局限，本文提出了AgenticRL框架。该框架利用多模态GPT智能体自主生成任务特定奖励函数、训练策略并评估反馈，从而在奖励设计、策略优化和部署方面增强了无人机导航任务的自主性。
第一作者: Zeyi Liu · 方向: 机器人操作 · 来源: cs.RO
人机交互强化学习信用分配机器人操作偏好校准样本效率
Abstract:Human-in-the-loop reinforcement learning (HIL-RL) improves sample efficiency in real-robot manipulation through online human intervention. However, successful trajectories may include suboptimal actions that deviate from the desired task-execution path and force human intervention. Existing HIL-RL methods typically apply the consistent credit assignment principle to all transitions, uniformly propagating discounted terminal rewards through suboptimal segments, ignoring the actual contribution of each transition to task success. This overestimates Q-values for critic learning and indirectly misguides actor updates toward suboptimal behavior patterns. To this end, we propose PACT, a Preference-calibrated Actor-Critic Training framework that leverages the implicit preference signals induced by intervention to perform credit reassignment on identified suboptimal segments while...
论文介绍 该研究针对人机交互强化学习（HIL-RL）中，对所有转移均匀分配信用导致Q值过高估计的问题，提出了PACT框架。它利用人类干预所产生的隐式偏好信号，对识别出的次优行为段进行信用重新分配，旨在引导策略学习更优的行为模式，提升机器人操作任务的学习效率。
第一作者: Mutian Tong · 方向: 机器人操作 · 来源: cs.RO
机器人操作3D 点云动作表示视频预测通用性
Abstract:Video-Action Models (VAMs) leverage the broad visual dynamics captured by pre-trained video diffusion models, offering a promising path toward generalizable robot manipulation. However, RGB-only video rollouts are not directly actionable: they leave metric 3D motion, contact geometry, and fine-grained spatial constraints under-specified, making action grounding ambiguous. Meanwhile, scaling action supervision across diverse tasks and embodiments remains costly. We present PointAction, a framework that bridges video predictions to robot actions through explicit point-based 4D modeling. PointAction fine-tunes a foundation video generation model to jointly predict future RGB frames and dynamic 3D pointmaps, producing temporally consistent 3D motion of task-relevant scene geometry. These point dynamics serve as a structured, embodiment-agnostic action interface, which a...
论文介绍 本文提出PointAction框架，旨在解决视频预测模型难以直接用于机器人动作执行的问题。其核心是微调视频生成模型，使其同时预测未来RGB帧和动态3D点图，将点云的运动作为与具体形态无关的动作表示接口，从而将视觉预测转化为可执行的机器人控制指令。
第一作者: J. Francisco Presenza · 方向: 具身智能 · 来源: cs.RO
多机器人系统姿态估计方位角刚性理论分布式
Abstract:This letter proposes a novel distributed bearing-based pose estimator for time-varying multi-robot systems. The method uses angles computed from body-frame bearings to estimate the robots' positions in $\mathbb{R}^3$ without knowledge of their orientations. The orientations in $\mathrm{SO}(3)$ are recovered from the estimated positions, the bearings, and the bearing derivatives. The proposed observer only requires the (directed) sensing topology to be \textit{angle-rigid}, a weaker condition than the commonly used ones like bearing rigidity. Local uniform exponential stability of the proposed observer is established under the assumption of persistently exciting motions for a subset of robots. Simulations are presented and discussed to evaluate the scheme's effectiveness and practicality.
论文介绍 该研究提出了一种新颖的分布式方位角姿态估计器，适用于时变多机器人系统。该方法利用本体坐标系下的方位角计算来估计机器人在三维空间中的位置，无需已知机器人朝向，再通过估计值和方位角导数恢复姿态。其要求的传感拓扑满足“角刚性”这一比方位角刚性更弱的条件。
第一作者: Vasco Carvalho · 方向: 具身智能 · 来源: cs.RO
语义加权ICPLiDAR里程计点云配准动态环境鲁棒性
Abstract:LiDAR odometry is a fundamental component of autonomous robotic systems, relying on geometric registration between consecutive point clouds to estimate ego-motion. However, traditional geometric approaches often degrade in dynamic or unstructured environments due to unreliable correspondences caused by moving objects, sparse geometric features, vegetation, and semantically ambiguous structures. Existing works have shown that, some of these limitations can be addressed by introducing semantic information from the environment in the registration process. In this work, we build on this, and show that not all elements in the environment are equally relevant for registration. Hence, we propose a semantic class-weighted ICP for LiDAR odometry. Instead of strictly filtering out points belonging to specific semantic classes, the proposed approach weights the residuals of points...
论文介绍 LiDAR里程计依赖点云配准估计自运动，但在动态或非结构化环境中，因移动物体、稀疏几何特征等问题导致传统几何方法性能下降。现有方法通过引入语义信息来改进，但并非所有环境元素对配准同样重要。本文提出一种语义类加权的迭代最近点（ICP）方法用于LiDAR里程计。该方法不严格过滤特定语义类别的点，而是根据语义类别对点的残差进行加权，从而提升配准在复杂环境中的鲁棒性。
第一作者: Xiangdong Feng · 方向: 具身智能 · 来源: cs.RO
去噪方差动作分块机器人策略自适应重规划流模型
Abstract:Action chunking has become a common inference strategy for flow-based robot policies, improving action coherence by modeling multi-step temporal dependencies in demonstrations. However, the execution horizon is still typically set as an empirical fixed value, overlooking that predictable free-space motions and precision-critical interaction phases often require different replanning frequencies. In this work, we first show that the denoising process of flow-based policies contains an intrinsic signal of task phases: clean-action estimates remain stable during predictable motion phases, but fluctuate more strongly around contact-rich or precision-sensitive operations. Motivated by this observation, we propose DVAC (Denoising-Variance Adaptive Chunking), a test-time method that adaptively determines how many actions to execute from each predicted chunk. DVAC measures the variance...
论文介绍 动作分块是基于流的机器人策略的常用推理策略，但执行范围通常为固定经验值。本文发现流策略的去噪过程包含任务阶段的内在信号：在可预测运动阶段，动作估计稳定，而在交互阶段波动较大。基于此，提出了去噪方差自适应分块（DVAC）方法，在测试时通过测量去噪方差来确定每次预测后应执行的动作数量，以实现自适应的重规划频率。
第一作者: Rodrigo Pérez-Dattari · 方向: 模仿学习 · 来源: cs.RO
流匹配动力系统模仿学习Lyapunov稳定性生成模型
Abstract:Flow matching has recently emerged as a powerful approach for imitation learning, enabling scalable, expressive, and multimodal motion policies. However, incorporating formal stability guarantees into these generative models, a prerequisite to ensure safe and generalizable robot behaviors, remains a significant challenge. While modeling robot motions as dynamical systems allows for such stability-based inductive biases, existing frameworks struggle to capture the rich action distributions inherent in complex robotic tasks. This paper introduces Stable Flow Matching Dynamical Systems (SFMDS), a novel framework that bridges the gap between high-capacity generative modeling and formal Lyapunov stability guarantees. SFMDS parametrizes dynamical systems via flow matching while simultaneously constraining the model to a family of stable solutions. We propose two variants: a soft...
论文介绍 流匹配是用于模仿学习的强大方法，但如何融入以保证安全性的形式化稳定性证明仍是挑战。本文提出了稳定流匹配动力系统（SFMDS）框架，弥合了高容量生成建模与形式化Lyapunov稳定性保证之间的差距。SFMDS通过流匹配来参数化动力系统，同时将模型约束在一系列稳定解中，旨在学习既具有表达能力又具备理论安全保证的运动策略。
第一作者: Sara Adeli · 方向: 机器人操作 · 来源: cs.RO
Fin Ray效应软抓手有限刚性单元法农业机器人力控制
Abstract:Fin Ray-inspired soft grippers offer a promising solution for gently handling delicate, irregular objects, especially in agriculture. The objective of this research is to design, fabricate, and model a Fin Ray Effect (FRE) soft gripper finger to enable precise force control in future applications. This design aims to gently grasp delicate agricultural products, such as tomatoes, that require both adaptability and accurate force application. To address the inherent challenges of soft robotics, including nonlinear behavior, infinite degrees of freedom, and variable material properties, the Finite Rigid Elements Method (FREM) was employed for modeling. This method preserves analytical accuracy while providing a reliable foundation for the development of a force controller in later stages. A detailed Finite Element Model (FEM) was created using ANSYS, and the analytical results...
论文介绍 受Fin Ray效应启发的软抓手在处理不规则物体方面具有潜力。本研究旨在设计、制造和建模一个Fin Ray效应软抓手手指，以实现精确的力控制，目标应用于农业中对番茄等精细产品的柔顺抓取。为了应对软体机器人建模的非线性挑战，采用了有限刚性单元法（FREM）进行建模，该方法在保持解析精度的同时，为后续力控制器的开发提供了可靠基础。
第一作者: Nicolas Gorlo · 方向: 具身智能 · 来源: cs.RO
记忆选择贝叶斯惊喜场景图空间记忆机器人问答
Abstract:Robots solving generalist tasks need to be able to ground instructions in their past experience, since humans may refer to notable past events when giving a task (e.g., ``Take me to where the chemical spill happened yesterday''). Since memory limits make storing all past events infeasible, long-term robot memory must be selective, ideally retaining only those episodes with high utility for future tasks. However, future tasks are not typically given a priori for generalist robots. To select generically useful memories, we propose Bayesian surprise as a gating mechanism for memory formation. We present an approach to compute surprise in a semantically rich deployment-agnostic latent space provided by V-JEPA-2. Using our gated episodic memory to augment 4D scene graph-based spatial memory, we show a consistent improvement over state-of-the-art benchmarks in robot question...
论文介绍 通用机器人需要将指令与过往经历关联，但记忆有限，需选择性存储。本文提出将贝叶斯惊喜（Bayesian surprise）作为记忆形成的门控机制，以选择对未来任务可能有用的episodes。该方法利用V-JEPA-2提供的语义丰富的潜在空间计算惊喜度，并用此门控记忆增强基于4D场景图的空间记忆，在机器人问答等基准测试中表现优于现有技术。
第一作者: Nan Sun · 方向: VLA 通用模型 · 来源: cs.RO
具身思维链视觉-语言-动作模型大规模数据集操作泛化
Abstract:Embodied chain-of-thought (CoT) aims to bridge linguistic reasoning and robotic control, but its effective form and integration strategy remain underexplored. In this paper, we revisit embodied CoT for vision-language-action (VLA) models at large scale. We construct the largest embodied CoT corpus to date, comprising 978,743 trajectories, 226.3M samples, and 2592.5 hours of robot data. Through extensive experiments, we find that effective embodied CoT should ground high-level semantic understanding into concrete action guidance, such as end-effector movement descriptions and image-space trajectories, while high-level reasoning alone brings only marginal gains. We further show that explicit CoT does not scale reliably when used as an autoregressive action prefix, as it suffers from compounding inference errors and unstable reasoning-action coupling. To address these...
论文介绍 具身思维链旨在连接语言推理与机器人控制，但其有效形式尚不明确。本文为大规模视觉-语言-动作（VLA）模型重新审视了具身思维链，并构建了迄今最大的具身思维链数据集。实验发现，有效的具身思维链应将高层语义理解转化为具体的动作指导，如末端执行器描述或图像轨迹，而仅进行高层推理收益甚微。同时指出，作为自回归动作前缀的显式思维链存在扩展性问题。
第一作者: Jessica Wenninger · 方向: 数据集与评测 · 来源: cs.RO
人机交互自中心跟踪身份切换社交机器人外观重识别
Abstract:To enable meaningful human-robot interaction (HRI), a robot must continuously assess engagement by consistently tracking users over time. State-of-the-art computer vision models, however, are heavily optimized for surveillance or autonomous driving. A social robot faces distinct egocentric challenges, such as humans bouncing, obstructing each other, or leaving the frame. Frequent identity switches (IDSW) cause the robot to lose its footing mid-conversation. To address this, we introduce a novel, custom-annotated egocentric dataset collected via the Furhat robot to capture complex social dynamics. We present a systematic evaluation isolating detection errors from tracking logic, comparing face versus body tracking, and assessing the impact of extended spatial memory and appearance re-identification (ReID). Results indicate that increasing spatial memory mitigates prolonged...
论文介绍 社交机器人需要持续跟踪用户以评估交互状态，但现有视觉模型多针对监控场景，难以应对自中心视角下人体遮挡、出框等挑战，频繁的身份切换会中断交互。本文通过Furhat机器人收集了一个新颖的自中心数据集，并系统评估了人脸与身体跟踪、扩展空间记忆以及外观重识别（ReID）的影响。结果表明，增加空间记忆有助于缓解长时间的身份切换问题。
第一作者: Xinhai Li · 方向: 导航与运动 · 来源: cs.RO
视觉语言导航3D高斯泼溅导航数据生成强化学习仿真平台
Abstract:Embodied navigation connects intelligent agents with the physical world and is fundamental for general robotic intelligence. Limited availability and quality of navigation data have constrained Vision-and-Language Navigation (VLN) systems' generalization and long-horizon capabilities. To address this, we curate diverse 3D scenes and develop an automated pipeline for large-scale navigation data, resulting in the GN-Matrix dataset. Building on a 3D Gaussian Splatting (3DGS) engine, we introduce a high-fidelity simulation platform supporting interactive roaming and collision-aware navigation. We further propose GN-Bench, the first BEV-based benchmark incorporating dynamic 3DGS avatars for human-robot interaction evaluation. To leverage the simulator, we develop an RL-driven navigation foundation model, Break and Establish (BAE). After supervised learning, DAgger exposes the model...
论文介绍 视觉语言导航（VLN）系统受限于导航数据的可用性和质量。本文通过策划多样化3D场景并开发自动化流程，生成了大规模的GN-Matrix数据集。基于3D高斯泼溅（3DGS）引擎，构建了支持交互漫游和碰撞感知导航的高保真仿真平台，并提出了首个BEV基准GN-Bench。此外，还开发了一个由强化学习驱动的导航基础模型BAE，并通过DAgger进一步优化。
第一作者: Ziyang Chen · 方向: VLA 通用模型 · 来源: cs.RO
视觉-语言-动作模型持续学习经验回放灾难性遗忘PHASER
Abstract:Vision-Language-Action (VLA) models have achieved remarkable success in language-conditioned robotic manipulation. However, deploying these models in open-ended environments requires continuously acquiring novel skills, a process that inevitably triggers severe catastrophic forgetting of previously learned behaviors. While experience replay (ER) serves as a standard mitigating strategy, naive uniform sampling fundamentally misaligns with the temporal characteristics of manipulation trajectories. It systematically under-samples brief but causally critical sub-skills, leading to phase starvation, and completely overlooks the varying degrees of forgetting across historical tasks. To overcome these limitations, we introduce PHASER, an architecture-agnostic continual learning framework. PHASER employs a phase-centric capacity allocation to guarantee equal memory support for all...
论文介绍 本文针对视觉-语言-动作模型在开放环境中持续学习新技能时引发的灾难性遗忘问题，提出PHASER框架。该框架采用阶段感知和语义经验回放，通过阶段中心容量分配和语义感知采样来优化样本处理，以缓解传统经验回放方法对操纵轨迹时间特性不匹配导致的阶段饥饿和遗忘差异，从而提升模型在机器人操纵中的持续学习能力。
第一作者: Xiaofei Wang · 方向: VLA 通用模型 · 来源: cs.RO
视觉-语言-动作模型对抗性补丁攻击部分可观测机器人安全注意力机制
Abstract:Vision-language-action (VLA) models are gaining attention in robotics, yet their robustness to adversarial attacks remains largely unexplored. Existing work shows that adversarial patches can mislead VLA-based robots but assumes full access to the entire execution trajectory, an unrealistic requirement in practice. We address this limitation by formulating a partially observable threat model, where the adversary can exploit only a short prefix of the trajectory to generate a fixed patch applied to all subsequent frames. Under this setting, we propose a two-phase framework. First, we localize the patch using the model's attention maps to identify visually critical regions that correspond to the full instruction. Then, we optimize the patch to disrupt the semantic grounding of target objects and increase the curvature of action trajectories, thereby compounding failures in both...
论文介绍 本文研究视觉-语言-动作模型在机器人中的鲁棒性，针对现有对抗性攻击需完全访问轨迹的不现实假设，提出部分可观测威胁模型。攻击者仅利用短前缀轨迹生成固定补丁，通过模型注意力图定位视觉关键区域，并优化补丁以破坏目标物体的语义接地和增加动作轨迹曲率，从而在现实场景中揭示VLA模型的安全风险。
第一作者: Sicong Gao · 方向: 具身智能 · 来源: cs.RO
机器人仿真GPU加速Isaac Sim数据生成物理建模
Abstract:Simulation has become a core infrastructure for robotics research. Unlike previous simulators, NVIDIA Isaac Sim leverages GPU acceleration to enable large-scale parallel training and physics-accurate modeling. Its synthetic data generation pipeline alleviates the scarcity of high-quality training data, supporting data-driven robot learning and large-scale simulation-centric experimentation. However, existing surveys often treat it as one simulator among many, without a systematic analysis of its architectural characteristics, usage patterns, and limitations. This survey reviews Isaac Sim from system and application perspectives, outlining its architecture and comparing it with widely used simulators. We analyze representative studies across five major domains and summarize common usage patterns, particularly in data generation and high-fidelity simulation. We also outline key...
论文介绍 本文系统综述NVIDIA Isaac Sim仿真器，从系统和应用视角分析其GPU加速架构、合成数据生成管道和物理建模能力。通过比较其他常用仿真器，总结其在五个机器人研究领域的应用模式，特别关注数据生成和高保真仿真的优势，并指出关键局限性，为机器人研究提供仿真基础设施的全面指南。
第一作者: Yanhui Lu · 方向: 机器人操作 · 来源: cs.RO
触觉感知事件传感器接触角估计静态表示动态表示
Abstract:Event-based tactile sensing offers low-latency signal acquisition for contact-rich robotic interaction. This paper investigates contact-angle estimation using event streams from an event-based tactile sensor (NeuroTac) and compares three event-derived spatial contour representations: a dynamic representation capturing recent event activity, a static representation recovering a more persistent contact state, and their combined representation. Across the evaluated motion scenarios, all representation pipelines exhibited P99 processing latency below 10 ms at all tested sampling intervals, demonstrating their potential for high-frequency event-based tactile angle estimation in robotic manipulation. The static representation consistently achieved marginally better performance than the dynamic and combined representations under scenario-specific training, yielding a mean overall MAE...
论文介绍 本文研究使用事件传感器进行触觉接触角估计，比较三种事件派生的空间轮廓表示：动态表示捕获近期事件活动，静态表示恢复持久接触状态，以及组合表示。实验评估显示所有表示管线在低采样间隔下处理延迟低于10毫秒，适用于高频触觉估计，其中静态表示在特定训练场景下性能略优，支持机器人操纵中的实时触觉反馈。
第一作者: Tianchen Huang · 方向: 具身智能 · 来源: cs.RO
人形机器人风格迁移全身控制仿生框架物理执行
Abstract:Expressive whole-body motion is important for humanoid robots operating in human environments, where robots are expected to move stably while presenting readable and adjustable body behaviors. However, most expressive motions are still obtained from fixed demonstrations or manually designed scripts, making it difficult to reuse a demonstrated style across different motion contents. Inspired by the way human motion styles convey affective and intentional cues through gait rhythm, posture, arm swing and body sway, this paper proposes a bionic generation-to-control framework for exemplar-driven style transfer on humanoid robots. Given a short human style exemplar and a target content motion, the proposed framework generates a stylized whole-body reference that preserves the intended motion content while transferring the demonstrated style. A physics-aware multi-condition latent...
论文介绍 本文针对人形机器人表达性运动难以跨内容重用风格的问题，提出仿生生成到控制框架。给定短人类风格样本和目标内容运动，该框架生成风格化全身参考，通过物理感知多条件潜变量模型确保执行可行性，同时迁移演示风格中的节奏、姿势等特征，提升机器人在人类环境中的运动可读性和可调整性。
第一作者: Charbel Abi Hana · 方向: 导航与运动 · 来源: cs.RO
路径规划草图引导扩散模型模仿学习自主移动机器人
Abstract:Path planning is essential for Autonomous Mobile Robots (AMRs). Conventional methods for incorporating human preferences into planning typically rely on either complex reward engineering or hardware-intensive solutions. Recent state-of-the-art frameworks leverage imitation learning to train behavior-specific path planning models from expert demonstrations. However, these approaches face two key limitations: limited generalization to unseen environments and low robustness in demonstration collection. To address these challenges, this work introduces an enhanced framework that focuses on two main contributions: an overhauled annotation tool built on ROS 2, and a novel training strategy that integrates diffusion-based augmentation into baseline behavioral cloning models. A dataset of expert demonstrations is provided and evaluated through ablation studies to assess the robustness...
论文介绍 本文提出SPADE框架，用于增强自主移动机器人的路径规划。针对传统方法偏好整合困难和模仿学习泛化性有限的问题，框架通过草图引导和扩散专家增强行为克隆模型，引入基于ROS 2的注释工具和扩散增强训练策略，提供专家演示数据集，并通过消融研究评估其在多样环境中的鲁棒性和适应性。
第一作者: Tianchen Huang · 方向: 模仿学习 · 来源: cs.RO
运动重定向人形机器人无监督学习CycleGAN形态差异
Abstract:Retargeting human motion to humanoid robots is critical for teleoperation, imitation learning and human-robot interaction. However, it remains challenging because of substantial morphological discrepancies between humans and robots, including differences in skeletal topology, limb proportions and degrees of freedom, as well as the scarcity of paired motion data. This paper presents Human2Humanoid, an unsupervised motion retargeting framework that transfers human motions to humanoid robot behaviors with high fidelity. To bridge the domain gap under unpaired data, we adopt a CycleGAN-based architecture equipped with a skeleton-aware graph convolutional network to capture topology-dependent motion features. To address cross-domain scale mismatches, we introduce a morphology-invariant end-effector consistency loss that aligns normalized end-effector trajectories to preserve motion...
论文介绍 本文提出Human2Humanoid，一个无监督运动重定向框架，用于将人类运动转移到人形机器人。针对形态差异和配对数据稀缺的挑战，采用CycleGAN架构和骨架感知图卷积网络捕获拓扑依赖特征，并引入形态不变端点一致性损失对齐归一化轨迹，以保持运动保真度，支持遥操作、模仿学习和人机交互应用。
第一作者: Jinyuan Zhang · 方向: VLA 通用模型 · 来源: cs.RO
具身人工智能开源平台视觉-语言-动作模型机械臂硬件软件统一
Abstract:Embodied AI in the real world requires both accurate hardware and robust vision-language-action (VLA) policies. We present OpenEAI-Platform, a fully open-source platform that integrates a low-cost 6+1 degree-of-freedom (dof) robotic arm (OpenEAI-Arm) and a reproducible VLA model (OpenEAI-VLA). OpenEAI-Arm provides open-source mechanical designs for low manufacturing cost and compliant control methods for higher accuracy. OpenEAI-VLA builds on Qwen3-VL-4B and uses a Diffusion Transformer action head, and is trained in two stages with only open-source robot and multimodal datasets. Across four real-world manipulation tasks, OpenEAI-Arm outperforms two commercial 6+1-dof arms under the same policy, and OpenEAI-VLA achieves success rates comparable to the large-scale pretrained pi0 baseline with only limited pretraining data. We will release the full hardware designs, drivers...
论文介绍 本文提出OpenEAI-Platform，一个开源具身AI硬件-软件统一平台，集成低成本6+1自由度机械臂和可复现的VLA模型。机械臂设计开源，采用低成本制造和精确控制；VLA模型基于Qwen3-VL-4B和扩散Transformer动作头，仅用开源数据训练。实验显示在真实操纵任务中性能优越，为具身AI研究提供可复现基础设施。
第一作者: Jiahao Xu · 方向: 机器人操作 · 来源: cs.RO
机器人操作抓取规划失败归因诊断优化长时程任务
Abstract:In robotic manipulation, the tight coupling between grasping and motion planning often obscures the true source of failure, leading to inefficient trial-and-error. To enable efficient long-horizon manipulation, we propose GTP-FA (Grasp-Then-Plan with Failure Attribution), a task-oriented two-stage grasp-then-plan framework that generates grasp candidates and performs downstream motion planning conditioned on the selected grasp. Given a failed manipulation trajectory, we learn a failure attribution model that generalizes to unseen grasps and produces a stable distribution over failure modes for diagnosis-guided optimization. Based on these attribution results, we then optimize both modules in a diagnosis-driven manner: on the grasping side, we inject task-level priors and risk penalties into grasp candidate scoring and optimization to suppress unstable or task-incompatible...
论文介绍 针对机器人操作中抓取与运动规划耦合紧密导致故障源难以定位的问题，本文提出了GTP-FA框架。该框架将抓取生成与下游运动规划分为两个阶段，并学习一个可泛化的失败归因模型。基于归因结果，以诊断驱动的方式优化抓取评分和运动规划，从而提升长时程操作任务的精确性与成功率。
第一作者: Aoduo Li · 方向: 导航与运动 · 来源: cs.RO
四足机器人自主导航图书馆场景ROS 2动态环境
Abstract:Libraries require autonomous robots to move quietly through narrow aisles while remaining safe around readers, chairs, bags, and carts. This paper presents a ROS 2 navigation system for a Unitree Go2 Edu quadruped equipped with a 4D LiDAR, a front depth camera, and an IMU. Rather than assuming the library is rough terrain, we target the practical mobility discontinuities of real deployments, including floor transitions, temporary clutter, and partially blocked passages where low-clearance wheeled platforms are less tolerant. RTAB-Map is used for visual-LiDAR SLAM, AMCL and EKF-based sensor fusion provide localization, and a Nav2 stack with A* and DWA supports planning and local avoidance. In a real library, the system achieves 100%, 96%, and 88% success rates in static, low-density dynamic, and high-density dynamic scenes, while map validation against surveyed control...
论文介绍 本文为面向图书馆场景的四足机器人设计了一套基于ROS 2的自主导航系统。系统搭载4D激光雷达、深度相机和IMU，利用RTAB-Map进行视觉-激光SLAM，并集成Nav2导航栈。该系统有效应对了地面过渡、临时 clutter及部分堵塞通道等实际挑战，在真实图书馆的不同动态场景中取得了较高的导航成功率。
第一作者: Rui Zhang · 方向: 机器人操作 · 来源: cs.RO
多任务强化学习GPU并行训练示教引导机器人操作基准构建
Abstract:Large scale GPU-parallel reinforcement learning has changed what can be trained in robot simulation, yet most systems still optimize one specialist policy per task. We propose a construction methodology for turning structured manipulation task families into GPU-parallel multi-task RL benchmarks, and instantiate it as MT-Libero using LIBERO assets and task predicates in Isaac Lab. The resulting benchmark supports simultaneous reinforcement learning over heterogeneous task suites with parallel rendering, physics randomization, and state-input or visual-input policies. To make such training practical under sparse success signals and limited prior data, we further propose DGPO, an on-policy demonstration guided method that combines importance weighted PPO with adaptive behavior cloning on matched demonstration actions. DGPO enables a tunable preference toward demonstrated task...
论文介绍 本文提出了一种构建GPU并行多任务强化学习基准的方法，并实例化为MT-Libero。该基准支持对异构任务套件进行并行训练。为解决稀疏奖励下的训练难题，论文进一步提出了DGPO方法，该方法将重要性加权PPO与自适应行为克隆相结合，利用示教数据引导策略优化，提升了多任务学习的效率与效果。
第一作者: Jongwook Han · 方向: 数据集与评测 · 来源: cs.RO
价值对齐家用机器人评测基准人机价值冲突场景生成
Abstract:While household robots are often evaluated based on task completion, everyday domestic environments involve value-conflicting situations in which robots are expected to choose actions that prioritize other values than task success, such as human autonomy, efficiency, or social appropriateness. Yet, there are no benchmarks for evaluating robots' value preferences in such scenarios. We introduce RobotValues, a benchmark to evaluate household robot planners in 10K value-conflict scenarios. Each instance consists of a realistic household image with multiple plausible robot actions that prioritize different human values. We construct RobotValues through LLM-assisted scenario generation, stakeholder-grounded value extraction, image generation and automatic quality control. Using RobotValues we evaluate VLMs used in robotics and find that models exhibit default value preferences...
论文介绍 家用机器人在面对价值冲突情境时，需要做出超越单纯任务完成的选择。然而，目前缺乏评估机器人价值偏好的基准。本文提出了RobotValues基准，包含1万多个现实家庭场景下的价值冲突案例。研究利用该基准评估了多个视觉语言模型，发现模型存在默认的价值偏好倾向，为机器人价值对齐研究提供了新的评测工具。
第一作者: Jeonguk Kang · 方向: 机器人操作 · 来源: cs.RO
人形机器人负载自适应域适应全身控制跨仿真迁移
Abstract:Humanoid loco-manipulation requires stable whole-body control under varying object masses and pickup/placement heights. This becomes particularly challenging in sim-to-real transfer, where object-induced load variation and robot-side dynamics mismatch interact during physical contact. Existing history-based adapters often compress these factors into a single latent representation, which can weaken robustness under heavy-load manipulation. We propose \textbf{SplitAdapter: Load-Aware Humanoid Loco-Manipulation via Factorized Adaptation}, which freezes a pretrained box manipulation policy and extends it with object/load and dynamics-aware context encoders trained with split world-model objectives, GRL-based cross-adversarial regularization, and hierarchical Feature-wise Linear Modulation (FiLM). In sim-to-sim experiments and real-world deployment, SplitAdapter improves Full-task...
论文介绍 人形机器人的移动操作在面对变化的物体质量和抓取高度时，需要稳定的全身控制，尤其是在仿真到现实的迁移中。本文提出SplitAdapter，它冻结一个预训练的箱子操作策略，并引入分离的物体/负载和动力学上下文编码器进行因子化适应。通过结合世界模型目标与对抗正则化，该方法增强了在重载操作下的鲁棒性。
第一作者: Qian Zhao · 方向: 机器人操作 · 来源: cs.RO
灵巧操作跨体态低成本示教数据生成强化学习
Abstract:Dexterous manipulation learning has long been hindered by the high costs of data and training, as pure reinforcement learning typically requires large-scale interactive exploration and imitation learning depends on high-quality demonstrations that are expensive to collect. To address this problem, we propose EaDex, a multi-embodiment dexterous manipulation learning framework under low-cost demonstration conditions, which enables rapid generation of demonstration data and consequently reduces training time for efficient dexterous manipulation. At the data level, EaDex captures human hand motions using only a single RGB-D camera and constructs structured demonstration data through MANO-based hand modeling, data normalization, and motion retargeting. At the learning level, we introduce a contact-reward-based dynamic demonstration annealing mechanism, which guides early-stage...
论文介绍 灵巧操作学习面临数据与训练成本高昂的挑战。本文提出了EaDex框架，旨在利用低成本示教条件实现跨体态灵巧操作学习。在数据层面，它仅用单个RGB-D相机捕获人手动作并构建结构化示教数据。在学习层面，引入基于接触奖励的动态示教退火机制，以引导策略从模仿平滑过渡到自主探索，从而提升学习效率。
第一作者: Zian Liu · 方向: 导航与运动 · 来源: cs.RO
无人机导航世界模型泛化能力强化学习零样本迁移
Abstract:Navigating a drone in unseen and cluttered environments requires reliable generalization to unseen scene layouts and understanding of environmental structure relative to the robot's capabilities. Previous methods, which assume the same environment configuration, often rely heavily on human-designed perception pipelines and predefined rules to guide the robot toward the target. This process is environment-dependent and generalizes poorly across environments. Inspired by animal navigation behavior, we design a navigation framework that navigates with a reinforcement-learning-based policy on top of a world-model-based environment understanding to overcome these issues. In addition, a sparse reward function without hand-crafted shaping terms is designed to avoid local minima traps and encourage yaw control behaviors. In simulation and on real drones, our method exhibits emergent...
论文介绍 在未知杂乱环境中导航要求无人机具备泛化能力。本文受动物导航行为启发，设计了一个结合世界模型与强化学习策略的导航框架。该框架利用世界模型理解环境结构，并训练策略在稀疏奖励下执行。该方法减少了对预设规则和感知流水线的依赖，在仿真和真实无人机上均展现出对新场景的泛化导航能力。
第一作者: Yizhi Chen · 方向: VLA 通用模型 · 来源: cs.RO
VLA模型空间对齐几何监督状态引导操作策略
Abstract:Current Vision--Language--Action (VLA) models often optimize for semantic grounding, whereas executable manipulation requires geometry-aware spatial alignment and dynamic affordance selection. We introduce GeoAlign, a state-guided spatial alignment architecture for VLA policy learning. GeoAlign post-trains an RGB geometry branch with robot-domain RGB-D supervision, yielding RGB-derived Geometry-Enhanced Post-Trained (GEP) features for policy rollout. The robot's proprioceptive state queries the GEP feature grid, producing compact, phase-dependent geometry tokens for action prediction. GeoAlign achieves 99.0% on LIBERO, 85.3% across three SimplerEnv-Fractal tasks, and 78.8% on eight geometry-critical real-world ALOHA tasks, with ablations confirming the value of geometry post-training and proprioceptive-state-guided querying.
论文介绍 当前视觉-语言-动作模型主要关注语义接地，但可执行的操控需要几何感知的空间对齐。本文提出了GeoAlign，一种用于VLA策略学习的状态引导空间对齐架构。它通过RGB-D监督对RGB几何分支进行后训练，并利用机器人本体状态查询特征网格，生成阶段相关的几何token用于动作预测，在多个基准任务上取得了良好效果。
第一作者: Zhe Sun · 方向: 具身智能 · 来源: cs.RO
机器人讲故事互动系统自然语言交互群体机器人儿童教育
Abstract:Robot storytelling offers a unique blend of technological innovation and creative expression that engages children in unprecedented ways. However, the technical aspects are often too complicated for children. We propose an interactive system that facilitates robot storytelling with tangible and natural language interactions. Children arrange the playground with their own stuff and create narratives with an LLM agent. The created narratives are transformed into a motion sequence based on the map and characters, and the motions are executed by self-navigating swarm robots. This system enhances robot storytelling with flexible scenarios, enabling young children to create robot dramas with everyday objects.
论文介绍 该研究提出一个互动系统，旨在简化机器人讲故事技术，使其更易被儿童使用。系统允许儿童通过布置玩具和自然语言交互与LLM代理共同创建叙事，并将叙事转化为运动序列，由自导航群体机器人执行。这种方法增强了机器人讲故事的灵活性，使幼儿能够利用日常物品创作机器人戏剧，应用于教育和娱乐领域。
第一作者: Yutong Liang · 方向: 机器人操作 · 来源: cs.RO
机器人操作运动跟踪强化学习约束优化双变量更新
Abstract:Human demonstrations provide strong priors for robot manipulation, yet it is non-trivial to transfer them to execute on real robots due to the kinematic gap. In dexterous manipulation, it remains challenging to track long-horizon, contact-rich sequences even in simulators: a reference-tracking policy must keep objects on their target trajectories while preserving demonstrated joint motion and contact timing. Existing approaches often rely on hand-crafted reward tuning that require per-sequence tuning and break under limited interaction budgets. We introduce ConTrack, a reinforcement learning (RL) framework that scales with tracking data. ConTrack treats object tracking as a constraint and allocates remaining control authority to motion fidelity, which allows it to adapt task--style trade-offs online using a dual-variable update. In addition, ConTrack also stabilizes...
论文介绍 该研究针对机器人操作中人类演示转移的挑战，提出ConTrack强化学习框架。该框架将物体跟踪视为约束，分配控制权限于运动保真度，并通过双变量更新在线调整任务与风格的权衡。这有助于在有限交互预算下稳定长时间、接触密集的操作序列，提高演示转移的准确性和稳定性。
第一作者: Aarav Bedi · 方向: 机器人操作 · 来源: cs.RO
模仿学习假成功检测可观测性机器人操作视觉检测
Abstract:Imitation-learning policies for robot manipulation inherit the quality of the success labels attached to their training episodes, and those labels are usually produced by the robot's own success check. A particularly damaging error is the false success: an episode the robot logs as a success when the task outcome was actually wrong. We ask a narrow but practical question about these episodes. Once an episode has already been flagged as a success, how much of the information needed to overturn that label is present in proprioception, and how much requires vision? We build a simulated testbed on two bimanual ALOHA tasks, induce failures through environment perturbations rather than label edits, label every episode by privileged simulator state that the detector never sees, and keep only episodes the robot flagged as successful. We then compare detectors restricted to...
论文介绍 该研究探讨机器人操作中模仿学习策略的假成功问题，即机器人将错误任务标记为成功。通过在模拟双臂任务中诱导环境扰动失败，比较仅使用本体感觉和结合视觉的检测器对假成功的可观测性。结果表明视觉信息在检测中至关重要，有助于提高训练数据的质量和策略的可靠性。
第一作者: Wenbo Zhang · 方向: VLA 通用模型 · 来源: cs.RO
视觉-语言-动作模型测试时训练潜在提示优化分布偏移自适应
Abstract:Vision-Language-Action (VLA) models trained on large-scale data have made remarkable progress, but they remain vulnerable to distribution shifts at deployment time. Recent VLA models suggest that prompts can serve as an efficient interface for steering policy behavior, but existing prompt-based steering typically relies on external guidance. This raises a natural question: can test-time training (TTT) for VLA be achieved by optimizing a prompt, so that the steering interface itself can be learned and adapted from interaction? We address this question with TTT-VLA, a test-time training framework based on Latent Prompt Optimization (LPO). During training, the latent prompt is learned with an additional proxy task, providing an extra learned conditioning signal for policy learning. At test time, TTT is performed by collecting interaction data from the current environment and...
论文介绍 该研究解决视觉-语言-动作模型在部署时面临分布偏移的问题。提出TTT-VLA框架，基于潜在提示优化实现测试时训练。训练阶段通过代理任务学习潜在提示，测试阶段通过交互数据优化提示以适应当前环境。这使模型能够自适应地调整策略行为，提高在现实世界任务中的性能。
第一作者: Gina Yoon · 方向: 机器人操作 · 来源: cs.RO
代码生成机器人控制大语言模型闭环调试模块化合成
Abstract:Large Language Models (LLMs) have demonstrated impressive performance across various domains, including code generation and problem solving. However, their application in robotic control, particularly in low-level tasks that require precise manipulation, real-time feedback, and environment-dependent execution, remains limited. To address this challenge, we propose the Closed-Loop Modular Code Synthesizer framework. This framework leverages a pre-trained LLM without any task-specific fine-tuning to perform modular code planning and generation, and iteratively executes the generated code while inserting debugging probes to observe its behavior. This closed-loop structure facilitates systematic debugging and refinement, ultimately producing executable control programs. We apply the proposed framework to the calibration of an RGB-D camera and a robotic arm, validating its...
论文介绍 该研究提出闭环模块化代码合成器框架，用于机器人控制的底层代码生成。利用预训练LLM进行模块化代码规划和生成，通过迭代执行和插入调试探针观察行为，实现系统调试和优化。应用于RGB-D相机和机械臂校准，验证了框架的有效性，无需任务特定微调。
第一作者: Maciek Popik · 方向: 数据集与评测 · 来源: cs.RO
动力学建模柔性机械臂混合模型高斯混合模型数据驱动
Abstract:This paper examines three approaches for modeling the dynamics of a flexible-link 2-DoF robotic arm to address unmodeled dynamics not captured by rigid-body models. Two physics informed models combine rigid-body dynamics (RBD) formulations with a Gaussian Mixture Model (GMM) to capture residual model errors and linkage flexibility. A kinematics-based regression model serves as a purely data-driven baseline. Using an open-source dataset, torque predictions are first estimated using Ridge regression on kinematic features, while the physicsbased baseline is constructed from published specifications, and ordinary least-squares regression is subsequently used to estimate the same parameter set directly from data. Results show that the physics-based parameters yield the poorest accuracy, while regularized and least-squares estimators align more closely with measured torques...
论文介绍 该研究探索柔性二自由度机械臂的动力学建模方法，以解决刚体模型未捕获的未建模动力学。提出两种物理信息模型结合刚体动力学和高斯混合模型，以及一个纯数据驱动基线。使用开源数据集进行扭矩预测评估，结果显示正则化和最小二乘估计器比物理基础参数更准确，表明混合建模能有效提高精度。
第一作者: Nikolaj Hindsbo · 方向: 数据集与评测 · 来源: cs.RO
自然语言代理边缘计算相机控制视觉理解基准测试
Abstract:Deploying language-driven agents in robotics requires evaluations that reflect real-world task demands: natural-language instructions with reproducible outcomes. Such agents must connect language models to callable perception and control tools, and be assessed using deployment-critical metrics including latency, accuracy, and error modes. We present SCOPE (Simulation and Camera Operations for Perception and Evaluation), a modular agent for natural-language, open-vocabulary pan-tilt-zoom (PTZ) camera control and visual scene understanding, designed explicitly for edge deployment. SCOPE operates both in a Blender-based simulation environment and on a physical PTZ camera, executing all perception, planning, and control locally at the deployment site using edge-accessible compute. We release a 536-task benchmark spanning QA, single- and multi-step commands, counting, spatial...
论文介绍 该研究提出SCOPE模块化代理，实现自然语言驱动的PTZ相机控制和视觉场景理解，专为边缘部署设计。代理在模拟和物理环境中执行，所有感知、规划和控制本地进行。发布了一个536任务基准测试，评估语言指令下的性能，包括问答、命令执行等，强调部署关键指标如延迟和准确性。
第一作者: Jaehyeon Son · 方向: VLA 通用模型 · 来源: cs.RO
视觉-语言-动作模型演示条件空间定位可见性感知跨体现
Abstract:Vision-language-action models (VLAs) are promising general-purpose robot policies, but adapting them to new tasks typically requires costly task-specific teleoperation data. As an alternative, we study one-shot demo-conditioned VLAs, where a robot policy is conditioned on a single demonstration video of an unseen task. We find that existing end-to-end approaches often struggle when successful execution requires precisely localizing small target regions. To address this limitation, we propose SeeTraceAct, a demo-conditioned VLA framework that encourages precise spatial grounding through visibility-aware prediction of future end-effector traces. To enable reproducible evaluation with cross-embodiment demonstrations, we introduce and release RoboCasa-DC, a demo-conditioned extension of RoboCasa with episode-paired humanoid videos. Experiments on RoboCasa-DC and a real-world...
论文介绍 该研究提出SeeTraceAct框架，用于从跨体现演示视频中学习机器人策略。针对现有方法在精确定位小目标区域时的局限，通过可见性感知预测未来末端执行器轨迹来增强空间定位。引入RoboCasa-DC数据集，支持可重复评估。实验表明该框架能有效适应新任务，减少对任务特定数据的依赖。
第一作者: Yueh-Hua Wu · 方向: VLA 通用模型 · 来源: cs.RO
视觉-语言-动作模型泛化视觉证据预算轨迹重新标记接口简化
Abstract:Generalization remains a central bottleneck for vision-language-action (VLA) models: under distractors, appearance shifts, and semantically similar tasks, the policy must often infer local execution details from coarse instructions while also deciding which parts of the image matter for control. We present S2 (See Less, Specify More), a framework for improving VLA generalization by training the executor under a cleaner interface. Specify More preserves the original instruction as a stable high-level goal while relabeling each trajectory into refined trajectory- and subtask-level language that disambiguates the current execution mode. Unlike native attention, See Less imposes an explicit visual evidence budget, training the executor to act from task-sufficient evidence rather than unconstrained visual context, without any region or mask annotation. This interface lets the...
论文介绍 针对视觉-语言-动作（VLA）模型在干扰物和外观变化下的泛化瓶颈，本文提出S2框架。该框架通过「Specify More」重新标记轨迹为精炼语言以明确执行模式，并通过「See Less」施加视觉证据预算，训练执行器基于任务足够证据行动，无需区域标注。这提高了VLA模型的泛化能力，适用于机器人操作等场景。
第一作者: Zongyuan Shen · 方向: 导航与运动 · 来源: cs.RO
动态环境运动规划经典方法学习方法综述
Abstract:Motion planning in dynamic environments requires robots to continuously adapt their paths in response to environmental changes for safe and uninterrupted navigation. While many surveys have reviewed planning in static settings, systematic reviews focused on dynamic environments remain limited. This paper presents a comprehensive survey of 138 works, primarily published between 2015 and 2025, spanning both classical and learning-based approaches. The motion planning methods are grouped into five categories based on the concepts of sampling, graph search, model predictive control, learning, and additional classical local planning approaches, including velocity obstacles, potential fields and dynamic windows. The learning techniques include supervised learning and reinforcement learning. We also discuss the role of dynamic perception in motion planning, covering techniques for...
论文介绍 本文系统综述了动态环境中的运动规划方法，涵盖138篇2015至2025年的论文。基于采样、图搜索、模型预测控制、学习等概念，将方法分为五类，包括经典局部规划如速度障碍和势场法。综述了动态感知技术的作用，为机器人安全导航研究和应用提供全面参考。
第一作者: Kyle Morgenstein · 方向: 策略学习 · 来源: cs.RO
模拟到现实策略学习sim2sim2real探索不足设计约束
Abstract:While sim2real efforts are necessary for effective policy transfer to hardware, there is such a thing as too much of a good thing. We argue that sim2real efforts have led to misaligned incentives with policy learning, resulting in simulator lock in and poor policy exploration due to the unreasonable constraints imposed by the real world. We offer a diagnosis and explanation of the current status of the problem, and propose a potential solution via a sim2sim2real paradigm that leverages the robot's kinematics as the sole design constraint.
论文介绍 本文指出模拟到现实（sim2real）努力过多可能导致策略学习问题，如模拟器锁定和探索不足，因现实世界不合理约束。作者诊断了当前状态，并提出sim2sim2real范式作为解决方案，仅利用机器人运动学作为设计约束，以改善策略转移和探索效率。
第一作者: Inhee Lee · 方向: 机器人操作 · 来源: cs.RO
3D场景重建单图像仿真就绪物理引擎机器人操作
Abstract:Reconstructing interactive, simulation-ready 3D scenes from a single image is a critical bottleneck for robotic manipulation. While recent single-image lifters recover plausible per-object shapes, composing them yields scenes that collapse under physical simulation due to interpenetrating, hovering, or sinking objects. Existing physics-aware methods address this strictly as a post-hoc layout correction, leaving the underlying geometric errors unresolved. To address this, we introduce SimuScene, a compositional 3D reconstruction pipeline that puts physics in the loop of shape and layout estimation. Rather than using physics merely for layout cleanup, we utilize the physics engine as a diagnostic measurement tool during the generative process itself. By diagnostically simulating reconstructed objects under gravity, we convert penetration and support failures into quantitative...
论文介绍 针对从单张图像重建交互式、仿真就绪3D场景的瓶颈，本文提出SimuScene管道。该方法将物理引擎集成到形状和布局估计中，通过诊断模拟重建对象在重力下的穿透和支撑失败，将其转化为定量损失，从而改善场景重建质量，支持机器人操作。
第一作者: Dan Jacobellis · 方向: 具身智能 · 来源: cs.RO
数据压缩自编码器云机器人一次转码高效重建
Abstract:In robotics systems, vast amounts of visual data are easily captured at high resolution using low-cost, low-power hardware. Yet, limited bandwidth and on-device compute resources prevent full utilization when transmitted via conventional codecs like JPEG/MPEG. Newer codecs, like AV1/AVIF, improve the rate-distortion trade-off, but demand far more resources for encoding, impractical without custom ASICs. Recent asymmetric autoencoders deliver high quality under extreme power and bandwidth constraints, but add prohibitive decoding cost and use bespoke formats that ignore decades of infrastructure built around standards like JPEG. To address these limitations, we introduce a compression framework for cloud robotics based on a Sensor Embedded Autoencoder paired with a One-Time Transcode for Efficient Reconstruction (SEAOTTER). Because the sensor, cloud, and consumer stages face...
论文介绍 本文针对机器人系统中视觉数据压缩的挑战，提出SEAOTTER框架。基于传感器嵌入自编码器进行压缩，并通过一次转码实现高效重建，以适应云机器人在有限带宽和计算资源下的需求，优化数据传输和处理效率。
第一作者: Xi Zheng · 方向: 具身智能 · 来源: cs.RO
具身AI可靠性测试形式验证生命周期保证
Abstract:Embodied AI systems are increasingly deployed in open-world environments, yet ensuring their reliability remains a fundamental challenge. Drawing on discussions from the AAAI'26 Bridge Program on "Making Embodied AI Reliable with Testing and Formal Verification", this article argues that reliability in embodied AI is inherently a lifecycle assurance problem arising from uncertainty, human interaction, and emergent behaviors across tightly coupled system components. We identify three complementary directions toward reliable embodied AI: (1) trustworthy scenario-based testing supported by validated specifications and meaningful coverage metrics, (2) compositional verification enabled by structured symbolic representations of system behavior and environmental context, and (3) runtime assurance mechanisms capable of adapting to uncertainty and distribution shifts during...
论文介绍 本文讨论具身AI系统在开放世界环境中的可靠性挑战，基于AAAI'26讨论，提出三个互补方向：基于场景的测试、组合验证和运行时保证。这些方向旨在通过不确定性、人机交互和涌现行为的管理，实现全生命周期可靠性保证。
第一作者: Xunyi Zhao · 方向: 导航与运动 · 来源: cs.RO
实例目标导航交互成本敏感不确定性减少信息增益
Abstract:Instance Goal Navigation (IGN) requires an embodied agent to find a specific object instance among distractors from an under-specified natural-language description. Such ambiguity often cannot be resolved from perception and language alone, making interaction with an oracle a natural mechanism for disambiguation. Prior interactive methods allow oracle queries but treat lightweight clarification and route-level guidance alike, letting agents boost success rate through repeated high-information questions rather than by resolving the underlying ambiguity efficiently. We recast interactive IGN as a cost-sensitive uncertainty-reduction problem, where the agent should ask the question whose answer provides the largest reduction in navigation uncertainty relative to its penalty. To this end, we apply an information-gain analysis on existing navigation corpora to identify which cues...
论文介绍 针对实例目标导航中模糊描述导致的歧义，本文将交互重新定义为成本敏感不确定性减少问题。代理应选择能最大化减少导航不确定性的问题，相对于其惩罚成本。通过信息增益分析现有导航语料库，识别有效线索，提高导航效率。
第一作者: Josef Chen · 方向: VLA 通用模型 · 来源: cs.RO
机器人策略内存管理递归内存动作门控常量VRAM
Abstract:The KV-cache is the right memory for datacenters but the wrong memory for robots. Datacenter inference batches many short requests and resets them, amortizing an attention cache across a crowd. Embodied agents instead run one long, non-resetting episode on bandwidth-limited edge hardware, where high-bandwidth memory and flash are scarce, flash has finite write endurance, and memory writes rather than compute can become the binding constraint. AURA-Mem (Action-Utility Recurrent Adaptive Memory) targets this regime. It wraps a frozen vision-language-action backbone with a constant-size recurrent memory and a learned gate that writes only when the current observation would change the next action: memory that knows when to stay silent. Unlike reconstruction-based memory, the gate is trained directly against a closed-loop action-error signal. Its inference state is fixed at 4,224...
论文介绍 本文指出KV缓存不适合机器人边缘硬件，因高带宽内存稀缺。提出AURA-Mem，用固定大小递归内存和学习门控包装冻结的视觉-语言-动作骨干，仅在当前观察改变下一动作时写入内存。这优化了内存使用，适用于常量VRAM场景。
第一作者: Zhengxian Huang · 方向: VLA 通用模型 · 来源: cs.RO
视觉-语言-动作模型思维链推理对抗性攻击行为劫持
Abstract:By integrating Chain-of-Thought (CoT) reasoning, Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation, particularly by improving generalization and interpretability. However, the security of CoT-based reasoning mechanisms remains largely unexplored. In this paper, we show that CoT reasoning introduces a novel attack vector for targeted behavior hijacking--for example, causing a robot to mistakenly deliver a knife to a person instead of an apple--without modifying the user's instruction. We first provide empirical evidence that CoT strongly governs action generation, even when it is semantically misaligned with the input instructions. Building on this observation, we propose TRAP, the first targeted behavior-hijacking adversarial attack against CoT-reasoning VLA models. By targeting the reasoning-to-action pathway, TRAP uses an...
论文介绍 研究针对视觉-语言-动作（VLA）模型中思维链（CoT）推理的安全性问题。论文提出 TRAP，一种基于对抗性补丁的攻击方法，能够劫持 CoT 推理过程，导致机器人行为偏离用户指令。例如，使机器人错误地将刀递给某人而非苹果。该工作揭示了 CoT 推理作为新攻击向量的风险，对 VLA 模型的安全应用具有重要警示作用。
美股方面，标普500 ETF（SPY）价格754.24，较52周高点仅低-0.81%，RSI14为67.9处于正常偏强区域，SMA20、SMA50和SMA200呈多头排列，显示上升趋势；纳斯达克100 ETF（QQQ）RSI超买至77.3，MACD金叉但价格微跌。加密货币市场整体承压，比特币价格62751.3，日内大跌-5.93%，RSI14仅17.3极度超卖，以太坊和Solana同样超卖，恐慌贪婪指数为12表明极度恐慌，总市值2.29万亿美元24小时下跌4.37%，BTC主导率55.1%。中概股多数走弱，阿里巴巴（BABA）价格127.21，RSI43.9，呈空头排列，拼多多和京东RSI在36-44区间，技术偏弱；腾讯控股（0700.HK）价格462，5日涨8.71%但趋势仍bearish。商品外汇中，黄金期货价格4485.9日内涨1.11%，但RSI中性；原油价格95.2，5日涨7.09%但RSI中性；美元指数99.46接近52周高点，多头排列，RSI59.5；美元兑人民币汇率6.77接近52周低，空头排列。整体市场技术面显示风险资产分化，加密市场超卖严重，避险资产相对稳定。
基于技术指标，QQQ当前价格744.21，日内微跌-0.26%但5日涨幅2.02%。RSI14达77.3，处于超买区域。MACD值21.7618与信号线21.6286形成金叉，价格接近52周高点仅差-0.59%，且SMA20、SMA50和SMA200呈多头排列，表明上升趋势完整，短期动量偏强，尽管可能面临调整压力。
比特币当前价格62751.3，日内大幅下跌-5.93%，5日跌幅-14.48%。RSI14仅为17.3，处于极度超卖状态。MACD值-2587.3605远低于信号线-1290.2522，柱状图负值扩大，价格远低于SMA20、SMA50和SMA200，形成空头排列，技术指标一致显示下行趋势持续。
英伟达当前价格214.75，日内下跌-3.62%，但5日上涨1.01%。RSI14为51.1，处于中性区域。MACD值3.7588低于信号线5.0435，趋势标记为bullish，价格在SMA20附近波动，多头排列存在。整体技术指标无强烈方向信号，状态中性。
10年期美债收益率当前为4.49，日内上涨0.81%，5日微涨0.22%。RSI14为53.5，中性偏上。MACD值0.0274略低于信号线0.0427，但趋势标记为bullish，价格高于SMA20、SMA50和SMA200，呈现多头排列，技术动量平稳偏上行。
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
风险提示：技术分析基于历史价格和指标数据，过去走势不代表未来表现。本报告的所有描述仅供技术指标解读参考，不涉及投资建议或市场预测。市场存在不确定性，投资者需自行承担风险。
The U.S.-brokered agreement called for “a complete cessation” of fire from Hezbollah, an Iranian-backed militia that operates in southern Lebanon. A previous cease-fire has largely been ignored.
中文摘要 以色列与黎巴嫩在美国斡旋下同意续签停火协议，要求伊朗支持的真主党武装「完全停止」开火。此前的停火协议基本未被遵守。
Greens and Coalition oppose discretionary powers that would allow the treasurer to make rule changes to CGT and negative gearing after the legislation passes. Follow today’s news live Get our breaking news email, free app or daily news podcast Jim Chalmers’ budget bill will face debate and a vote in
中文摘要 澳大利亚绿党与反对党联盟反对一项预算法案，该法案将赋予财政部长吉姆·查默斯在资本利得税和负扣税方面的自由裁量权。他们称这种「亨利八世权力」过于宽泛。
It was the latest attempt by President Trump to flip the narrative on a conflict that he once said would lead to quick and decisive victory.
中文摘要 美国总统特朗普表示，伊朗战争对美国「不是什么大事」。这是他试图改变此前关于这场冲突会迅速决断的言论的最新尝试。
Stunning rebuke to president as lawmakers vote 215-208 for measure forcing him to seek congressional approval The US House of Representatives delivered a stunning rebuke to Donald Trump over his war on Iran on Wednesday, as representatives backed a move to force him to seek approval from Congress or
中文摘要 美国众议院以215票对208票通过一项战争权力决议，要求总统在对伊朗采取军事行动前必须获得国会批准，这是对特朗普政府的重大制约。
Statement with US after Israel-Lebanon talks in Washington says agreement will create ‘pilot’ security zones in Lebanon from which Hezbollah banned One killed and 63 hurt in Iran attack on Kuwait airport as Trump says ceasefire talks ongoing The Kuwaiti defence ministry said it intercepted 13 ballis
中文摘要 以色列与黎巴嫩同意续期停火，美国众议院通过决议限制总统在伊朗的战争权力。此外，伊朗对科威特机场的攻击造成1人死亡、63人受伤。
In the 215-208 vote, four Republicans joined Democrats to pass the measure, which had failed in three previous attempts.
中文摘要 美国众议院以215票对208票通过一项决议，旨在停止伊朗战争，这是对特朗普的罕见政治打击。四名共和党人投了赞成票，此前该决议曾三次失败。
In a statement, the US State Department said both countries reject "any attempt, by any state or non-state actor, to hold Lebanon's future hostage."
中文摘要 以色列和黎巴嫩同意实施停火，条件是真主党停止攻击。美国国务院发表声明称，双方均拒绝任何企图「绑架黎巴嫩未来」的行为。
The Middle East is Japan’s main source of crude oil, from which naphtha is extracted and used to make items including printing ink and plastics Takeaways, supermarkets, and bakeries in Japan are running out of plastic bags, trays and food service gloves amid widening shortages of the key plastic ing
中文摘要 受伊朗战争影响，日本主要石脑油供应来源中东出现短缺，导致塑料袋、餐盒和手套等塑料制品供应紧张，多家商铺和超市面临缺货。
Lebanon's Health Ministry reports that 3,516 people have now been killed by Israeli attacks on the country since March.
中文摘要 美国与伊朗在波斯湾发生最新冲突后局势持续紧张。黎巴嫩卫生部报告，自三月以来，以色列的袭击已导致黎巴嫩3516人死亡。
Activists have tried to erect a statue of Marwan Barghouti in London’s Parliament Square, but police intervened.
中文摘要 活动人士试图在伦敦议会广场竖立被监禁的巴勒斯坦领导人马尔万·巴尔古提的雕像，但遭到警方干预。
中文摘要 信息不足，无法生成摘要。
Canada is the first G7 country to approve the lower cost weight-loss drugs, which are rolling out in pharmacies this month.
中文摘要 加拿大成为首个批准低价版糖尿病及减肥药Ozempic仿制药的G7国家，本月起将在药店上市。而美国尚未批准此类仿制药。
Despite long-established procedures for bringing Americans home for monitoring and treatment, the Trump administration has not said that it will allow those at risk of Ebola back into the country.
中文摘要 随着埃博拉疫情扩大，特朗普政府尚未制定明确应对计划，也未表示是否允许有感染风险的美国公民回国进行监测和治疗。
High fuel prices are strengthening the case for EV adoption in the world's third largest auto market.
中文摘要 高昂的燃油价格正推动更多印度消费者转向购买电动汽车，强化了电动车在全球第三大汽车市场的吸引力，但挑战依然存在。
Trump says he wants to keep talks on the conflict in Lebanon separate from negotiations over the war with Iran.
中文摘要 特朗普表示，他希望将黎巴嫩冲突的谈判与伊朗战争的谈判分开进行，试图将两者解耦。
A burial team was attacked and 11 Ebola patients fled isolation facilities in eastern Democratic Republic of Congo, as the outbreak spread to another health zone in the country’s hardest-hit province.
中文摘要 刚果民主共和国东部埃博拉疫情扩大，埋葬队遭袭，11名患者逃离隔离设施，疫情蔓延至该国受灾最严重省份的另一个卫生区。
Shares in chip company fall as much as 15% in after-hours trading
中文摘要 芯片公司博通因收入预测不及预期，市值蒸发逾3000亿美元，股价在盘后交易中最多下跌15%。
Quantinuum Inc., a quantum computing company backed by Honeywell International Inc., raised $1.68 billion in its upsized US initial public offering, demonstrating growing investor enthusiasm for the emerging technology.
中文摘要 霍尼韦尔支持的量子计算公司Quantinuum在美国IPO中扩大规模，筹集16.8亿美元，显示投资者对该新兴技术的热情增长。
Australian vintner Treasury Wine Estates Ltd. is expecting lower earnings for the current financial year as it looks to focus on solidifying key markets and bolstering its position in the luxury portfolio.
中文摘要 澳大利亚葡萄酒商Treasury Wine Estates预计本财年收益将下降，计划专注于巩固关键市场和增强奢侈品组合地位。
The Indonesian rupiah is closing in on a key psychological level, putting investors on watch for a stronger response from the central bank.
中文摘要 印尼盾逼近18,000关口，市场关注央行可能加强干预，投资者保持警惕。
Elon Musk’s SpaceX is poised to have the largest stock-market debut in history when it goes public later in June. SpaceX is aiming to raise $75 billion in the initial public offering, more than twice the previous record holder.
中文摘要 埃隆·马斯克的SpaceX计划于6月上市，目标在IPO中筹集750亿美元，有望创下历史最大股市首次亮相记录。
Gil Luria, DA Davidson Head of Technology Research, discusses the outlook for Broadcom as the Nvidia alternative releases its latest quarterly data. (Source: Bloomberg)
中文摘要 DA Davidson技术研究主管Gil Luria讨论博通的前景，作为英伟达的替代品，该公司发布最新季度数据。
Gold pushed higher after Israel and Lebanon agreed to a conditional ceasefire, a possible step toward resolving the wider Middle East conflict that’s upended global energy markets and raised inflation risks.
中文摘要 黄金价格走高，此前以色列和黎巴嫩达成有条件停火，这可能是解决中东冲突的步骤，该冲突影响了全球能源市场并推高通胀风险。
The more than $90bn hedge fund tells investors it will take longer to retrieve their money from two flagship funds
中文摘要 对冲基金DE Shaw将投资者锁定期延长至最长四年，该基金管理资产超过900亿美元，投资者从两支旗舰基金中赎回资金需更长时间。
Elon Musk’s space exploration company set a target price for buyers earlier than expected.
中文摘要 埃隆·马斯克的太空探索公司SpaceX估值达1.75万亿美元，接近股市上市，提前为买家设定目标价格。
UK-based investors pulled money from cash funds and piled into bonds last month, enticed by surging yields, according to fund flow data compiled by Calastone.
中文摘要 据Calastone基金流动数据，英国投资者上月受高收益率吸引，将资金从现金基金转向债券。
The rising popularity of lab-grown diamonds heaps pressure on those hunting for the natural gems.
中文摘要 人造钻石日益普及，对天然钻石开采行业造成压力。
6 回复 · 程序员 节点
20 回复 · 程序员 节点
7 回复 · 程序员 节点
7 回复 · 程序员 节点
7 回复 · 程序员 节点
15 回复 · 程序员 节点
11 回复 · Apple 节点
8 回复 · Apple 节点
23 回复 · Apple 节点
17 回复 · Apple 节点
不知不觉加入L站快1年了，加入的时候生日已过，这是我在L站的第一个生日，祝自己天天开心，也祝社区越来越好！ 60 个帖子 - 57 位参与者 阅读完整话题
首字效果： codex公益站：https://new.sharedchat.cc/ 群内佬友评价： 一个人一个号不要重复注册，会风控 73 个帖子 - 62 位参与者 阅读完整话题
本帖使用社区公益推广，符合推广要求。我申明并遵循社区要求的以下内容： 我的项目是免费使用的，无收费（变相收费、赞助）部分： 是 我的帖子已经打上 公益推广 标签： 是 我的项目属于个人项目，与公司或商业机构无关： 是 我的项目不存在QQ、TG等群组引流： 是 我的项目不存在非运营必要的网站引流： 是 我的项目不存在为他人推广、AFF： 是 我的项目无关联的商业项目： 是 我的站点存在登录，并已接入 LINUX DO Connect： 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 以下为项目介绍正文内容，AI生成、润色内容已
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 以下为项目介绍正文内容，AI生成、润色内容已使用截图方式发出 github.com GitHub - fish2018/webhtv: WebHomeTV 基于FongMi二次开发，增强了 WebHome 自定义首页、App... WebHomeTV 基于FongMi二次开发，增
greasyfork.org Linux.do Boost 增强 选中 boost 后增加 @ 按钮，一键打开回复框并 @ 该 boost 用户 27 个帖子 - 14 位参与者 阅读完整话题
给它临时开的权限模式，让我帮我排查下什么导致电脑卡顿，查完以后说让我重启，重启以后直接不见了。。。 18 个帖子 - 18 位参与者 阅读完整话题
昨天看到佬友写的帖子 【π】关于pi的完善之路，package生态的折腾之路 感觉真心不错，刚睡醒，心血来潮也来分享一下自己近期折腾 pi 扩展的经验。 先给误入此帖 (bushi) 的佬介绍下， Pi 是一个轻量实现的 harness, 跟 claude code / codex / opencode 这些工具比起来绝对是简易甚至可以称得上是毛坯房了，很多功能作者都刻意避开，这也让它的 system prompt token 开销很小。 虽然 Pi 这类 agent 可应用的领域不止 coding，但我目前主要还是用于 coding。本贴推荐的都是一些基础插件，coding 场景还是都能用得
Map of Intl 是一个属于两个人的旅行记录应用。 最开始只是想解决一个很简单的问题： 旅行结束后，照片越来越多，但回忆却越来越难整理。 于是我尝试用 AI 和 Vibe Coding 的方式，做了一个能够记录共同生活的小程序。 它将地图、时间线、旅行计划与回忆整理融合在一起，把一起去过的城市、走过的路线、拍下的照片和重要纪念日串联成完整的故事。 随着记录越来越多，地图上的足迹会不断增长，时间线也会越来越长。 后来发现，它记录的不只是旅行。 而是两个人一起走过的生活。 希望多年以后再次打开时，依然能够看见那些共同经历过的风景和时光。 可自由编辑路线 可查看旅行日记 接入高德地图API 3
这是你不仁别怪我不义。我是你忠实粉丝，就这样回报我。你彻底成功的让我对你失望透顶 我这么纯都不行 既然你很喜欢发验证码是吧，那我就写个脚本让你全国发，不要停 37 个帖子 - 31 位参与者 阅读完整话题
如果有特别想关注的，可以在提示词中说的更清楚一些，codex拿到的数据还是蛮完善的，我现在就是每天看一下，太忙，最近都空仓着，没咋关注这些。 提示词（可根据需求自行修改，我样式上做了一些细微的调整，不好总结出来了[token 我没算过，我开的pro20x 会员，这个具体会跑多少token，我没细看过，记得注意哈，万一撑不住就不好了]）。 github链接：GitHub - ningzaichun/ai_stock_daily_report: codex ai stock daily report · GitHub 大家感兴趣可以看看，完整提示词和使用的案例都在里面。 49 个帖子 - 28 位