Python · ★ 23,176 · 🍴 2,219 · 📈 844 stars today
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
中文介绍 针对时间序列预测任务，Google Research 开发了预训练基础模型 TimesFM。它旨在通过大规模预训练学习通用的时间序列模式，帮助数据科学家和分析师更高效、准确地预测未来趋势，减少针对特定数据集的特征工程和模型调优工作。
Rust · ★ 10,006 · 🍴 463 · 📈 369 stars today
IP addresses break, dial keys instead. Modular networking stack in Rust.
中文介绍 Iroh 是一个用 Rust 编写的模块化网络栈，旨在解决依赖不稳定 IP 地址进行通信的问题。它提倡“拨号密钥而非 IP 地址”，为构建点对点（P2P）应用提供更可靠、灵活的基础网络层，适合需要去中心化连接的开发者。
TypeScript · ★ 449,542 · 🍴 45,128 · 📈 417 stars today
freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.
中文介绍 这是 freeCodeCamp 的开源代码库与课程。它是一个面向全球的免费编程学习平台，通过交互式课程和项目，教授数学、编程及计算机科学知识，适合编程初学者和自学者系统性地入门和提升。
Shell · ★ 232,414 · 🍴 20,644 · 📈 1,429 stars today
An agentic skills framework & software development methodology that works.
中文介绍 Superpowers 是一个代理技能框架与软件开发方法论。它旨在为构建具有“超能力”的 AI 代理提供一套实用的结构和方法，帮助开发者定义、组合和评估代理技能，从而开发出更有效、可靠的代理驱动型应用。
★ 4,126 · 🍴 432 · 📈 202 stars today
GLM-5: From Vibe Coding to Agentic Engineering
中文介绍 GLM-5 是智谱 AI 发布的大型语言模型。其项目描述指向“从氛围编码到代理工程”的转变，暗示该模型专注于提升代码生成与智能代理（Agent）构建能力，旨在帮助开发者将自然语言意图转化为更可靠的工程化实现。
C · ★ 7,042 · 🍴 567 · 📈 2,322 stars today
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
中文介绍 这是一个高性能的代码智能 MCP 服务器，能将代码仓库索引为持久化的知识图谱。它支持 158 种语言，查询在毫秒内完成，并能大幅减少大语言模型处理代码时的 token 消耗，适合用于构建代码分析、检索和理解工具。
Python · ★ 1,778 · 🍴 203 · 📈 124 stars today
Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
中文介绍 Hyper-Extract 是一个利用大语言模型从非结构化文本中提取结构化知识的工具。它能通过一条命令，将文本转换为图、超图以及时空关系等多种结构化表示，适用于知识图谱构建、信息抽取和数据建模场景。
C++ · ★ 11,221 · 🍴 650 · 📈 259 stars today
A lightweight, lightning-fast, in-process vector database
中文介绍 zvec 是阿里巴巴开源的轻量级、进程内向量数据库。它提供闪电般的向量相似性检索速度，适用于需要将向量搜索集成到应用程序内部的场景，如推荐系统、图像检索等，追求低延迟和高效能。
TypeScript · ★ 5,502 · 🍴 301 · 📈 162 stars today
The sandbox agent framework.
中文介绍 Flue 是一个代理沙箱框架。它提供一个受控的沙箱环境，用于安全地测试、开发和运行 AI 代理，确保代理在执行代码或访问外部资源时受到约束，适合需要安全隔离代理行为的开发者。
TypeScript · ★ 22,145 · 🍴 2,706 · 📈 1,345 stars today
Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.
中文介绍 Kilo 是一个一体化的代理工程平台。它集成了流行的开源编码代理，旨在通过代理技术加速软件开发、部署和迭代的全流程，帮助开发团队构建、交付和优化产品。
TypeScript · ★ 51,838 · 🍴 4,601 · 📈 613 stars today
🔥🔥🔥 Open-source Jira, Linear, Monday, and ClickUp alternative. Plane is a modern project management platform to manage tasks, sprints, docs, and triage.
中文介绍 Plane 是一个开源的项目管理平台，定位为 Jira、Linear 等工具的替代品。它提供任务管理、冲刺规划、文档编写和问题分流等现代化功能，帮助团队进行更灵活、可视化的项目管理。
TypeScript · ★ 38,681 · 🍴 2,293 · 📈 18 stars today
The open-source, cross-platform API client for GraphQL, REST, WebSockets, SSE and gRPC. With Cloud, Local and Git storage.
中文介绍 Insomnia 是一款开源、跨平台的 API 客户端。它支持 GraphQL、REST、WebSockets、SSE 和 gRPC 等多种协议，并提供云端、本地和 Git 存储功能，方便开发者设计、调试和测试 API。
Rust · ★ 7,925 · 🍴 340 · 📈 244 stars today
Cross-platform GUI written in Rust using ADB to debloat non-rooted Android devices. Improve your privacy, the security and battery life of your device.
中文介绍 这是一款用 Rust 编写的跨平台 GUI 工具，通过 ADB 移除未 root 的 Android 设备中的预装应用。它可以有效提升设备的隐私性、安全性和电池续航，适合希望清理系统臃肿软件的 Android 用户。
C# · ★ 38,097 · 🍴 10,710 · 📈 14 stars today
ASP.NET Core is a cross-platform .NET framework for building modern cloud-based web applications on Windows, Mac, or Linux.
中文介绍 ASP.NET Core 是一个开源的跨平台 .NET 框架，用于在 Windows、Mac 或 Linux 上构建现代化的云端 Web 应用程序和服务。它支持构建高性能、高可用的 API 和 Web 应用，是 .NET Web 开发的核心框架。
★ 14,397 · 🍴 2,335 · 📈 40 stars today
A curated list of Artificial Intelligence (AI) courses, books, video lectures and papers.
中文介绍 这是一个精心整理的人工智能（AI）资源列表，涵盖了课程、书籍、视频讲座和重要论文。它旨在为 AI 学习者、研究者和爱好者提供一站式学习指南和参考资料索引。
Python · ★ 7,493 · 🍴 1,208 · 📈 51 stars today
Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.
中文介绍 这是 LTX-2 音视频生成模型的官方 Python 包。它提供了模型的推理功能和 LoRA 微调训练工具，方便开发者和研究者使用该模型进行音视频内容生成、风格迁移等创作任务。
Python · ★ 14,979 · 🍴 1,534 · 📈 51 stars today
Free and Open Source Machine Translation API. Self-hosted, offline capable and easy to setup.
中文介绍 LibreTranslate 是一个免费开源的机器翻译 API。它支持自托管和完全离线运行，易于部署，为开发者提供了一种不依赖第三方云服务的、保护数据隐私的翻译解决方案。
@zodchiii · 22.7K 粉丝 · 1.2M 阅 · 500 赞 · 71 转
Most setups run agents once and hand you whatever comes out. A team that runs in loops keeps going until the work actually passes. Below is the setup in 3 files: the agents, the loop that drives
中文介绍 介绍如何构建一个循环运行的Claude Code代理团队，而非单次执行。提供了包含代理定义和驱动循环的三文件具体设置，使代理能够持续工作直至任务通过验证，超越了传统单次运行的局限。
@sairahul1 · 117.4K 粉丝 · 511.9K 阅 · 500 赞 · 84 转
Your AI agent works great for the first 10 steps. Then somewhere around step 15, it starts getting sloppy. Wrong tool calls. Forgetting your original instructions. Low-quality outputs. Most people
中文介绍 这是一份完整的上下文工程手册，旨在解决AI代理在长期任务中（如执行到第15步后）出现的性能下降问题，包括错误的工具调用和遗忘指令。它系统性地探讨了为代理设计和管理上下文的策略。
@0xMovez · 26.7K 粉丝 · 208.0K 阅 · 504 赞 · 59 转
A free open-source model is running 300 parallel agents across 4,000 coordinated steps from a single prompt, and it scores higher on real research tasks than models you pay 5x more for. Most people
中文介绍 介绍一个由免费开源模型Kimi K2.6运行、Opus 4.8验证的自改进代理群。该系统能在单次提示下并行运行300个代理，执行4000个协调步骤，在研究任务上的表现优于更昂贵的付费模型。
@jxnlco · 105.9K 粉丝 · 204.4K 阅 · 504 赞 · 47 转
Update: Computer Use is now Available in the EU/UK ;) Enjoy! There are three ways for Codex to use a computer: Computer Use, the Chrome extension, and the in-app browser. They overlap just enough to
中文介绍 介绍OpenAI Codex使用计算机的三种方式：原生计算机使用功能、Chrome扩展和应用内浏览器。文章比较了它们的重叠部分和各自适用场景，帮助用户根据需求选择。
@OracleMindAI · 21.0K 粉丝 · 105.0K 阅 · 2.8K 赞 · 582 转
In 2026, autonomous AI agents have become one of the most effective strategies on prediction markets. Over 30% of all activity on Polymarket now comes from algorithmic and AI-powered wallets. We
中文介绍 介绍ORACLE项目，让官方AI代理在预测市场Polymarket上进行自主交易。数据显示，到2026年，算法和AI钱包已占该平台超30%的活动，展示了AI代理在金融预测领域的实际应用与有效性。
@sydneyrunkle · 7.9K 粉丝 · 74.7K 阅 · 565 赞 · 87 转
Agents are useful because they help us automate work by taking actions in the real world. But getting agents to do valuable work reliably takes more than just a good model: it requires a carefully
中文介绍 探讨「循环工程」的艺术。指出让代理可靠地执行有价值的现实世界任务，不仅需要好的模型，更依赖于精心设计的工程来定义循环的工作流程、验证和终止条件。
@0xCodez · 8.2K 粉丝 · 72.8K 阅 · 508 赞 · 79 转
Everyone’s talking about loops. Almost no one is talking about what the loop runs on. 9 out of 10 builders run Claude Code on the default harness - no rules, no subagents, no hooks, no memory. Then
中文介绍 提出从单一代理构建自改进系统的14步路线图。强调90%的构建者忽略了基础运行环境的重要性，提供了关于规则、子代理、钩子和记忆等方面的具体工程建议。
@heynavtoor · 143.5K 粉丝 · 47.7K 阅 · 538 赞 · 70 转
Most people use Claude like a search box. Ask, answer, close tab. They are leaving the best feature locked. Save this :) Stanford built a research system called STORM. In peer reviewed testing it
中文介绍 介绍如何将斯坦福大学的STORM研究方法应用于Claude，使其能像博士一样进行深度研究。STORM系统在同行评审中表现优异，此方法旨在解锁Claude超越简单问答的深层研究能力。
@zachlloydtweets · 10.6K 粉丝 · 43.5K 阅 · 512 赞 · 53 转
There’s been a lot of chatter about using “loops” lately to drive agents, and I think this has been accompanied by a bit of “what actually is a loop”? I can’t speak for everyone else using the term,
中文介绍 澄清「循环」在驱动代理语境下的具体含义，并探讨如何为特定「技能」构建自改进循环。旨在为这个流行术语提供明确的技术定义和实现思路。
@kvnkld · 7.2K 粉丝 · 42.0K 阅 · 531 赞 · 25 转
People keep asking how the UI components I post end up looking so polished, or what prompts I use. So here’s a breakdown of the most important things: Polish is not a feature you prompt for. You can't
中文介绍 分享用Claude制作精致UI的10条核心规则。强调UI的精致度不能仅通过提示词获得，而是需要一套关于设计原则、系统化构建和细节打磨的工程方法。
@Just_sharon7 · 44.1K 粉丝 · 32.5K 阅 · 502 赞 · 18 转
If you're still switching between 10 tools to make UGC ads, analyze performance, and iterate... your workflow is outdated. Arcads just dropped MCP support, and pairing it with Claude (especially Fable
中文介绍 介绍广告工具Arcads新增了MCP支持，与Claude（特别是Fable模型）配合，可简化UGC广告的制作、性能分析和迭代流程，替代了原本需要切换多个工具的旧工作流。
@ActionModelAI · 57.8K 粉丝 · 5.7K 阅 · 501 赞 · 366 转
Most people think AI is still in its early stages. They're right. And that's exactly why these facts are so crazy. 1. AI could add $15.7 trillion to the global economy by 2030 According to PwC, AI
中文介绍 分享10个关于AI的惊人事实，旨在普及认知。涵盖经济影响、技术能力、发展速度和潜在风险等多个方面，提醒读者AI仍处于早期阶段但发展迅猛。
@OptimaiNetwork · 99.4K 粉丝 · 5.3K 阅 · 511 赞 · 360 转
The old internet was built for humans browsing pages, clicking ads, and buying subscriptions. The autonomous internet needs something else: live context, verified signals, permissioned execution, and
中文介绍 讨论「自主时代」的神经系统。指出为人类浏览设计的旧互联网架构无法满足自主AI代理的需求，新架构需要提供实时上下文、可信信号、权限执行和可验证的协调机制。
@Trade_OracleAI · 21.1K 粉丝 · 60 阅 · 2.8K 赞 · 584 转
In 2026, autonomous AI agents have become one of the most effective strategies on prediction markets. Over 30% of all activity on Polymarket now comes from algorithmic and AI-powered wallets. We
中文介绍 介绍ORACLE项目，让官方AI代理在预测市场Polymarket上进行自主交易。数据显示，到2026年，算法和AI钱包已占该平台超30%的活动，展示了AI代理在金融预测领域的实际应用与有效性。
中文介绍 Hugging Face博客探讨研究代理的保密能力，涉及MosaicLeaks项目，分析AI代理在信息保护方面的潜在挑战。
We talk about how this legendary investor went from humble beginnings in Singapore to leading rounds in Anthropic, Mistral, Black Forest Labs, and Periodic Labs... and the AMP secret master plan!
中文介绍 投资者Anjney Midha从新加坡起步，领导了对Anthropic、Mistral、Black Forest Labs和Periodic Labs等公司的投资轮次，并揭秘AMP的秘密计划。
OpenAI introduces new spend controls and usage analytics for ChatGPT Enterprise, helping organizations manage costs and scale AI with confidence.
中文介绍 OpenAI为企业版ChatGPT推出新的支出控制和使用分析功能，帮助组织管理成本并自信地扩展AI应用。
Learn how GPT-5.5 Instant improves ChatGPT’s health and wellness responses with stronger reasoning, better context, clearer communication, and physician-informed evaluations.
中文介绍 GPT-5.5 Instant提升ChatGPT的健康和福祉响应能力，通过更强推理、更好上下文、更清晰沟通和医生评估来改进性能。
Researchers used an OpenAI reasoning model to help diagnose rare diseases, identifying 18 new diagnoses in previously unsolved cases.
中文介绍 研究人员使用OpenAI推理模型帮助诊断罕见儿童遗传疾病，在之前未解决病例中识别出18个新诊断。
The only bootstrapped frontier lab announces its second product and second
中文介绍 Midjourney Medical作为自举前沿实验室的第二个产品，允许用户像称体重一样扫描器官，但具体功能细节有限。
中文介绍 Hugging Face博客讨论超越LoRA的微调技术，探索是否能击败最受欢迎的微调方法。
中文介绍 Hugging Face博客介绍基准测试开放模型在自定义工具上的代理能力，评估模型是否足够具有代理性。
中文介绍 ChatGPT市场份额下降，同时Vercel和Replit有新动态，如Replit链接Claude等AI发展事件。
Radical AI's Joseph Krause on why the moat in materials is the lab, not the model
中文介绍 Radical AI的Joseph Krause指出，在材料领域，护城河在于实验室而非模型，强调实验基础设施的关键作用。
中文介绍 MolmoMotion是一种语言引导的3D运动预测技术，由Allen AI开发，用于预测物体运动轨迹。
中文介绍 介绍从Hugging Face Hub到机器人硬件的路径，使用Strands Agents和LeRobot技术实现模型部署。
OpenAI and Molecule.one show how a near-autonomous AI chemist using GPT-5.4 improved a key drug-making reaction, advancing medicinal chemistry research.
中文介绍 OpenAI和Molecule.one展示近自主AI化学家使用GPT-5.4改进药物制造反应，推进药物化学研究进展。
中文介绍 GLM-5.2模型专为长时任务设计，提升AI在长时间跨度任务中的性能和效率。
We have a new top open model in the world!
中文介绍 GLM-5.2被宣布为世界顶级前端编码模型，并引入IndexShare技术用于推测解码，优化编码任务。
第一作者: Po-Han Cheng · 方向: 软件安全
代码安全间接提示注入防御机制Tree-sitterCST分析
Abstract:Code large language models increasingly retrieve external code context from repositories, documentation, issue threads, and coding-agent environments, creating an indirect prompt-injection surface where attackers hide instructions in comments, strings, identifiers, or decoy code. We propose CodeSentinel, a three-layer inference-time sanitizer. It uses Tree-sitter to extract high-risk model-facing CST nodes, then combines syntax-guided pre-filtering, CST-guided Dynamic Min-K\% scoring, and node perturbation analysis to detect adversarial and natural-looking semantic triggers. Detected nodes are removed or neutralized before reaching the downstream Code LLM. Across six recent attack families, \CodeSentinel achieves 0.80 average node-level F1, outperforming CodeGarrison, DePA, and KillBadCode.
论文介绍 针对代码大语言模型在检索外部上下文时面临的间接提示注入攻击问题，CodeSentinel提出了一种三层推理时防御系统。该系统利用Tree-sitter提取高风险代码节点，结合语法引导预过滤、CST引导的Dynamic Min-K%评分和节点扰动分析来检测并移除恶意触发器。实验表明，它在多个攻击家族中有效提升了代码LLM的安全性。
第一作者: Yu-Ting Lin · 方向: 软件安全
代理技能恶意代码注入供应链攻击VulMask漏洞利用
Abstract:Agent skills allow LLM-based coding agents to acquire domain-specific capabilities from third-party packages, but they also introduce a new supply-chain attack surface. We present PhantomSkill, an attack framework that hides malicious behavior in a skill's auxiliary resources rather than in its textual description. Its core technique, VulMask, rewrites overt malicious scripts into vulnerability-shaped implementations whose malicious behavior is activated only under attacker-controlled trigger conditions. This design shifts the visible signal from explicit malicious intent to ordinary-looking insecure code. Across representative host skills, attack goals, coding agents, generation models, and automated reviewers, VulMask preserves benign utility while reducing warning and malware-level detection compared with overt malicious scripts. Our results show that skill ecosystems...
论文介绍 PhantomSkill攻击框架针对基于LLM的编码代理技能生态系统，通过VulMask技术隐藏恶意行为于技能的辅助资源中。该技术将明显恶意脚本重写为漏洞形状实现，仅在攻击者控制的触发条件下激活恶意行为，从而绕过常规检测。这揭示了技能生态系统面临的新供应链攻击风险。
第一作者: Nahum Korda · 方向: 软件安全
漏洞发现代码分解LLM推理对抗验证动态测试
Abstract:Automated vulnerability discovery in large codebases remains challenging: traditional static analysis produces high false-positive rates, while dynamic approaches such as fuzzing require substantial infrastructure and often target narrow classes of bugs. Recent advances in large language models (LLMs) enable semantic reasoning about program behavior, but applying LLMs to repository-scale security analysis introduces challenges related to context management, cost, and verification. We present OpenAnt, an open-source vulnerability discovery system that integrates static program analysis with LLM-based reasoning in a multi-stage pipeline. OpenAnt introduces three key techniques. First, codebases are decomposed into self-contained analysis units filtered by reachability from external entry points, reducing the analysis surface by up to 97% while preserving attack-relevant code...
论文介绍 OpenAnt是一个开源漏洞发现系统，旨在解决大型代码库中自动化分析的挑战。它通过代码分解将代码库分为自包含单元以减少分析范围，集成静态程序分析与LLM的语义推理，并引入对抗验证和动态测试。该系统旨在提高漏洞发现的效率，减少误报，并支持安全研究。
第一作者: Ousmane Touat · 方向: 密码学协议
去中心化学习拜占庭鲁棒性机密聚合安全多方计算MPC
Abstract:Dealing simultaneously with confidentiality and Byzantine behaviors in decentralized learning is a challenging problem. Indeed, in decentralized learning, clients train a machine learning model while keeping their data locally and share their model parameters or gradients with a set of neighbors. While enforcing confidentiality calls for hiding the exchanged model parameters/gradients (e.g., by using cryptographic techniques), dealing with Byzantine contributions often requires inspecting the latter. Hence, most research works address these objectives separately. A recent line of work proposes to employ secure multi-party computation (MPC) to implement robust aggregators against model poisoning, thereby enforcing both confidentiality and Byzantine resilience. However, these solutions scale badly: they either require all-to-all communication between participants or delegate the...
论文介绍 Giskard旨在解决去中心化学习中同时保障数据机密性和抵御拜占庭攻击的挑战。传统方法通常分别处理这两个目标，而Giskard通过安全多方计算实现稳健聚合器，确保在参与者之间隐藏模型参数的同时，能够检测和缓解恶意贡献。这为大规模去中心化学习提供了隐私保护与安全性的统一解决方案。
第一作者: Alan Woodward · 方向: 安全研究
特殊访问系统妥协风险不确定性评估加密密钥安全架构
Abstract:Lawful exceptional access (EA) systems hold the cryptographic keys that decrypt protected communications for authorised parties. The debate over their risks has been long and qualitative, complicated by two problems: no public dataset of EA-specific compromise events exists, so assessment must use sparse, indirect evidence; and prior work has treated structurally different designs as equivalent, though transmission-layer EA in carrier infrastructure (T-EA) and over-the-top EA at the platform layer (OTT-EA) differ in how cryptographic keys relate to ciphertext data. This paper builds a structured uncertainty framework for evaluating systemic compromise risk in EA architectures. It does not produce predictive forecasts, which the evidence cannot support; it separates findings robust to assumptions from those that depend on calibration. Four analytical layers are applied to T-EA...
论文介绍 本文针对合法特殊访问系统的妥协风险评估，由于缺乏公共数据集和证据稀疏，构建了一个结构化不确定性框架。通过分析传输层EA和平台层EA的不同设计，该框架应用四个分析层，分离了依赖于假设的发现与稳健的发现。它为评估系统性风险提供了方法论，尽管不产生预测性预报。
第一作者: Faruk Alpay · 方向: 软件安全
漏洞分类可利用性评估证据图计算预算前瞻性分析
Abstract:Defenders cannot patch every newly disclosed vulnerability at once, so exploitability prediction must be evaluated prospectively rather than retrospectively. We study compute-budgeted vulnerability triage in which each CVE is scored only from public evidence visible by a fixed decision time. Advisories, exploit archives, fix commits, and hacker-community discourse are represented as a temporal evidence graph; a budgeted selector admits only a few evidence documents per CVE, and every score is paired with an auditable certificate listing the supporting signals, timestamps, source layers, and leakage flags. On 12012 prospective CVEs from public sources, budgeted evidence selection raises leakage-safe prospective recall@50 from 0.010 for a severity-only baseline to 0.026, while two evidence documents per CVE capture most of the value. A strong cross-encoder reranker lowers...
论文介绍 本文研究计算预算下的前瞻性漏洞分类问题，针对新披露漏洞的可利用性预测。通过构建时间证据图整合咨询、漏洞档案等公共信息，并使用预算选择器限制每个CVE的证据文档数量，系统为每个CVE提供可审计的评分证书。实验显示，少量证据文档即可捕获大部分价值，提升分类效率。
第一作者: Siyuan Pang · 方向: 软件安全
PyPI安全恶意包检测API知识库代理工作流静态分析
Abstract:The detection of malicious PyPI packages is crucial for maintaining the security of the open source software supply chain. Existing methods, which primarily rely on rules or traditional machine learning, suffer from poor interpretability and difficulty in adapting to novel attacks. To address this, we propose PYPILINE, a novel detection method that combines a suspicious API knowledge base with an Agent workflow. PYPILINE first conducts static analysis on known malicious packages, extracting abstract syntax trees and generating API call graphs, from which it automatically extracts and constructs a structured suspicious API knowledge base. During the detection phase, this knowledge base is used to enhance reasoning capabilities. Through an Agent workflow, PYPILINE performs in depth semantic analysis of unknown packages and outputs a structured, interpretable maliciousness...
论文介绍 针对PyPI恶意包检测的挑战，PYPILINE提出了一种结合可疑API知识库和代理工作流的新方法。首先通过静态分析对已知恶意包提取抽象语法树和API调用图，构建结构化知识库。在检测阶段，代理工作流利用该知识库对未知包进行深度语义分析，输出可解释的恶意性评估，提高检测的适应性和解释性。
第一作者: Gabriele Digregorio · 方向: 软件安全
ML模型安全生命周期分析动态检测恶意行为执行监控
Abstract:The growing reliance on pre-trained Machine Learning (ML) models has introduced new attack surfaces. Recent vulnerabilities demonstrate that malicious behavior can be embedded within model artifacts, often bypassing existing defenses. Current model-scanning solutions primarily rely on static, format-specific rules or known attack signatures, which limit their ability to generalize across frameworks and to detect novel exploitation paths. In contrast, we propose a solution that focuses on the effects an attack has on the host system executing the model and builds on foundational intuitions about ML model execution. In particular, we observe that ML models operate within well-defined lifecycle phases and that, within each phase, interactions with the host system are highly structured and predictable. We translate these intuitions into Moat, a dynamic lifecycle-aware approach for...
论文介绍 针对预训练ML模型可能嵌入恶意行为的问题，现有静态扫描方法泛化能力有限。本文提出Moat，一种生命周期感知的动态分析方法，基于ML模型执行的不同阶段（如加载、初始化）观察其与主机系统的结构化交互，从而检测攻击效应。这提供了对新型攻击路径的通用检测能力，增强模型执行环境的安全性。
第一作者: Moon Ye-Bin · 方向: 隐私保护
隐私保护任务完成主动隐私提取基准测试AI代理
Abstract:Agents are increasingly deployed in document-intensive workflows where sensitive private information is not an edge case but a routine input, e.g., an agent booking a flight needs passport numbers. In such settings, the agent must use private information to complete tasks accurately while never exposing it in its responses, because it cannot verify who is actually at the keyboard. These two obligations are in fundamental tension. A model capable enough to use private information for task completion can, by the same capability, be induced to reveal it. To evaluate the trade-off of task accuracy and privacy leakage, we introduce Task-completion and Resistance to Active Privacy-extraction (TRAP). Each scenario includes a document containing private information, a task query that requires the agent to invoke the correct tool using private fields, and an attack query that attempts...
论文介绍 本文针对AI代理在涉及敏感信息的工作流程中，任务准确性与隐私泄露之间存在根本性张力的问题。作者提出了名为TRAP的基准，旨在系统评估代理在利用私人信息完成任务时，抵御主动隐私提取攻击的能力。该基准包含需要调用特定工具的任务查询和试图诱导泄露的攻击查询，为权衡任务性能与隐私风险提供了评测框架。
第一作者: Mert Nakıp · 方向: AI 安全
低速攻击入侵检测物联网安全QoS预测早期检测
Abstract:Low-Rate Denial of Service (LDoS) attacks pose a significant challenge to IoT networks due to their subtle and prolonged nature, often evading traditional intrusion detection systems. This paper presents IDQS (Intrusion Detection via QoS Prediction), a lightweight and proactive framework for early LDoS attack detection. IDQS integrates two new key components: (i) RTP-QoS, a Recurrent Trend Predictive Neural Network that learns and forecasts future Quality of Service (QoS) based on historical traffic patterns, and (ii) PDM, a Pairwise Decision Model that evaluates discrepancies between predicted and actual QoS to identify potential attacks. Evaluated on the public SDN-SlowRate-DDoS and CIC-IDS2017 datasets, IDQS respectively achieves over 79% and 91% detection accuracy across most attack scenarios with high recall and low false negatives, while maintaining an end-to-end...
论文介绍 本文针对物联网网络中隐蔽且持久的低速率拒绝服务攻击难以检测的挑战，提出了一种轻量级、前瞻性的IDQS检测框架。该框架核心包括一个用于预测服务质量的循环趋势预测神经网络，以及一个通过对比预测与实际服务差异来识别攻击的成对决策模型。实验表明，该方法在多个数据集上能实现较高的检测准确率与召回率，有效实现早期预警。
第一作者: Xinjian Luo · 方向: AI 安全
隐私风险分布式推理多模态大语言模型图像提示中间嵌入
Abstract:Distributed large language model (LLM) inference frameworks connect isolated consumer-grade devices for large-scale model inference, substantially reducing hardware constraints. However, recent studies show that intermediate embeddings transmitted among participants can leak private prompts. As LLMs evolve into multimodal LLMs (MLLMs), this risk extends beyond text: image prompts contain rich visual and semantic information, making their intermediate embeddings highly privacy-sensitive. Yet, image-prompt leakage in distributed MLLM inference remains largely unexplored. In this paper, we investigate privacy risks to input images caused by intermediate embeddings in distributed MLLM frameworks. We first analyze the information flow from image pixels to intermediate representations. Since image and text embeddings are often intertwined across MLLM layers, we design an image...
论文介绍 随着分布式推理框架的普及，中间嵌入泄露用户输入隐私的风险也随之增加。本文首次系统研究了分布式多模态大语言模型推理中，图像提示所面临的隐私威胁。作者分析了从图像像素到中间表示的信息流，并设计了一种攻击方法，能够从传输的中间嵌入中重建原始图像提示，揭示了该场景下亟需关注的安全问题。
第一作者: Yong Yang · 方向: AI 安全
提示泄露大语言模型应用安全分析系统提示攻击防御
Abstract:Large language model (LLM)-based applications rely on system prompts to encode core logic and developer-defined constraints, making these prompts important intellectual property. However, system prompts are vulnerable to prompt leaking attacks. Although prior work has shown such attacks in controlled settings, their prevalence, causes, and defenses in real-world deployments remain unclear. This paper presents a systematic study of prompt leaking in real-world LLM-based applications. We measure 1,200 applications across six major commercial platforms and find that over 80% of deployments leak system prompts under realistic adversarial queries, sometimes exposing sensitive information such as third-party API keys. We also show that existing defenses often fail to prevent leakage without degrading usability. To explain these failures, we conduct an attention-level mechanistic...
论文介绍 本文对真实世界中基于大语言模型的应用面临的提示泄露风险进行了系统性研究。通过对六大商业平台上1200个应用的测量，发现超过80%的应用在常规攻击查询下会泄露系统提示，甚至暴露敏感的API密钥。研究进一步分析了现有防御措施的失效原因，并从注意力机制层面揭示了攻击的底层原理。
第一作者: Guo-Wei Wong · 方向: 安全研究
高级持续威胁日志分析序列分离生成式模型威胁狩猎
Abstract:In enterprise environments, multiple Advanced Persistent Threat (APT) campaigns often unfold concurrently, producing audit logs in which attack techniques across actors (sources) are interleaved over time. This setting naturally gives rise to an Unknown-K Interleaved Sequence Demixing (UKISD) problem: recovering multiple latent campaigns from an interleaved technique sequence while jointly inferring their number and technique-level assignments. Existing approaches, ranging from statistical pattern mining to provenance-based analysis, typically assume single-campaign settings or rely on rigid heuristics, limiting their effectiveness under realistic conditions involving overlapping campaigns, shared techniques, and variable execution lengths. We present Topic-Guided Consistency Modeling (TGCM), a generative disentanglement framework to tackle the UKSID problem. TGCM leverages...
论文介绍 在企业环境中，多个高级持续威胁活动常并发进行，导致审计日志中不同攻击者的技术序列相互交织。本文提出TGCM框架来解决从交织序列中分离出未知数量潜在活动的挑战。该生成式分离方法利用主题模型指导和一致性建模，能更有效地应对活动重叠、技术共享等复杂现实条件，提升威胁分析的准确性。
第一作者: Zhengxiong Luo · 方向: 软件安全
漏洞检测大语言模型代理安全规范可解释性自动化审计
Abstract:The advent of agentic vulnerability detection is already becoming a watershed moment for software security. Audits conducted entirely by autonomous LLM agents are uncovering critical vulnerabilities in fundamental software underpinning digital society. Many of these vulnerabilities remained masked for years, surfacing only now with AI agents. Yet the reasoning behind these discoveries remains alarmingly opaque and unvalidated. What assumptions did the agent make about a function's inputs when it deemed that function to be secure? Failures in reasoning and incorrect assumptions can lead to missed vulnerabilities and reduce trust in agentic analysis. We propose a security-specification-first paradigm that (1) exposes the agent's tacit assumptions explicitly as security specifications and (2) continuously refines those specifications via runtime falsification. We realize our...
论文介绍 本文提出一种面向代理式漏洞检测的“安全规范优先”新范式，并实现了Code-Augur系统。该方法强调显式暴露代理在判断代码安全性时所做的隐式假设，并将其转化为可验证的安全规范。通过运行时反证机制持续检验和修正这些规范，旨在提升自主漏洞检测过程的可解释性与可靠性，增强对其发现结果的信任。
第一作者: Qiqi Liu · 方向: 密码学协议
CAN总线安全入侵检测伪装攻击车辆安全双向Mamba
Abstract:The Controller Area Network (CAN) protocol is the primary communication standard for Electronic Control Units (ECUs) in modern vehicles, but its lack of encryption and authentication exposes it to a range of security threats. Existing intrusion detection systems are largely tuned to fabrication-style attacks (DoS, fuzzing, ID spoofing realised by frame injection), in which detection signals such as per-ID inter-arrival statistics are readily available. We instead address the harder \emph{masquerade} setting~\cite{b37}, in which an internal adversary substitutes a legitimate frame in-situ at its original transmission slot, preserving traffic periodicity and rendering traffic-statistic defences ineffective. We propose the Mamba Intrusion Detection System (MIDS), an innovative dual-stream framework that processes CAN identifiers and payloads in parallel and reconstructs their...
论文介绍 本文针对车载控制器局域网络中更隐蔽的“伪装”攻击（攻击者替换合法帧而非注入新帧），提出了一种创新的双流MIDS入侵检测系统。该系统并行处理CAN报文的标识符和载荷数据，并利用双向Mamba架构重建序列特征以识别异常。与主要检测注入攻击的传统方法相比，MIDS专门应对保持通信周期性的高级替换攻击。
第一作者: Laxmipriya Ganesh Iyer · 方向: AI 安全
AI安全间接提示注入工具合同门控机制LLM代理
Abstract:Risk-Aware Causal Gating (RACG) defends tool-augmented LLM agents against indirect prompt injection by removing dangerous tools from the agent's visible action space, so that even a fully injection-compliant agent cannot call a tool it cannot see. We make three points. First, this structural guarantee does not eliminate the trust assumption behind safe tool use; it relocates it into the integrity of the tool contracts -- declared preconditions, effects, risk, and authorization -- that the gate reads, so an attacker who corrupts a contract can make the gate mis-decide without ever persuading the agent. Second, forging a tool's effects is strictly more dangerous than tampering with its risk label, because RACG applies a causal gate before its admissibility gate: an off-path tool is never exposed, so risk-relabeling alone fails, whereas effect forgery routes the dangerous tool...
论文介绍 本文分析了风险感知因果门控机制在防御工具增强型大语言模型代理免受间接提示注入时的安全性。作者指出，该机制虽能隐藏危险工具，但其安全性依赖于所读取工具合同的完整性。攻击者通过篡改工具合同（特别是伪造效果），仍可诱导门控做出错误决策。基于此，文章提出了ContractGuard来强化合同层的安全保障。
第一作者: Victor Adama · 方向: 网络安全
网络安全意识大学生调查态度不一致性隐私管理钓鱼攻击
Abstract:Today's young adults are most immersed in technology, leading in feelings of powerlessness in managing online privacy across many platforms, and particularly susceptible to phishing attacks. This raises questions about their general, wide-ranging attitudes towards and management of cybersecurity. How do young, tech-savvy adults approach cybersecurity? We seek a better understanding of their cybersecurity knowledge, attitudes and experiences, in particular in addressing deceptive online communications. We surveyed a group of `lead users': computing university students (n = 236). By combining thematic analysis of open-ended responses with quantitative data, we provide insights into their experiences and perceptions. While students demonstrate reasonable cybersecurity awareness, their cybersecurity experiences vary, and inconsistencies exist around their practices, perceptions of...
论文介绍 本研究通过调查236名计算专业大学生，探讨他们对网络安全的态度、知识和经历。研究发现，学生虽具有基本网络安全意识，但在实践和感知上存在不一致性，尤其在应对欺骗性在线通信方面。方法结合主题分析和定量数据，为改善网络安全教育提供见解。
第一作者: Inderjeet Singh · 方向: 软件安全
AI沙箱威胁模型分类学测量框架软件安全
Abstract:AI systems are increasingly evaluated in bounded environments that combine isolation, simulation, instrumentation, supervision, and evidence capture. For physical AI, AIoT, and cyber-physical systems, this shift is not a matter of terminology: the system under test may sense, decide, actuate, communicate, and fail through physical processes, networked devices, and human operators. This article develops an assurance-oriented account of AI sandboxes as controlled environments for testing, evaluation, verification, and validation across digital AI, embodied autonomy, and cyber-physical deployments. We formalize the sandbox boundary and a weakest-link rule for composing per-dimension evidence into a bounded deployment claim; separate major sandbox archetypes; define a cyber-physical threat model that includes attacks on the assurance apparatus itself; and introduce a measurement...
论文介绍 本文提出一个面向保障的AI沙箱概念，作为测试、评估和验证AI系统的受控环境。它形式化了沙箱边界和最弱链接规则，定义了网络物理威胁模型，并引入测量框架。适用于数字AI、具身自主和网络物理部署，以确保系统安全性。
第一作者: Aaditya Pai · 方向: 安全研究
提示防御领域伪装攻击注入攻击大语言模型安全评估
Abstract:Domain-camouflaged injection attacks embed malicious instructions in retrieved content using domain-appropriate vocabulary, evading standard detectors that rely on syntactic injection markers. When detection fails, practitioners need to know which defense architectures reduce attack success. We evaluate five prompting-based defenses (spotlighting, paraphrasing, prompt sandwiching, and two combinations) against domain-camouflaged injection across three model families (Claude Haiku, Llama 3.1 8B, Gemini 2.0 Flash) and three deployment domains (financial, legal, general) using 3,510 trials. Paraphrasing retrieved content before agent processing is the most consistently effective defense in this benchmark, reducing camouflage attack success rate by 55-84\% depending on model, and achieves lower attack success rates than our Llama Guard 4 configuration on every model tested...
论文介绍 该研究评估五种基于提示的防御措施对抗领域伪装注入攻击，使用三种模型家族和三个部署领域进行3510次试验。结果表明，在检索内容后进行释义是最有效的防御，能显著降低攻击成功率。这为AI系统防御提供了实用方案。
第一作者: Fabio F.G. Buono · 方向: 软件安全
混合基数密钥一次性密码本霍纳分解均匀采样量子密钥分发
Abstract:The Mixed-Radix One-Time Pad (MR-OTP) extends the classical OTP to heterogeneous alphabets while preserving perfect secrecy. We provide a practical, bias-free method to convert raw binary entropy from a QKD source into uniform mixed-radix keys by identifying Horner's method and its inverse as the natural mapping between binary integers and mixed-radix tuples. We show that naive modular reduction induces bias and prove that rejection sampling restores uniformity with optimal expected cost. We establish end-to-end information-theoretic security for single and multi-session pipelines, quantify efficiency gains, present a batched extractor, and give unconditional and conditional results on the Base Recovery Problem.
论文介绍 本文扩展经典一次性密码本到混合字母表，提供无偏方法将QKD源的二进制熵转换为均匀混合基数密钥。使用霍纳方法及其逆映射作为自然转换，并证明拒绝采样恢复均匀性。建立端到端信息论安全，为密码系统提供实用工具。
第一作者: Chandranil Chakraborttii · 方向: 安全研究
向量数据库软删除数据恢复隐私合规HNSW
Abstract:Retrieval-augmented generation (RAG) allows large language models to access external and private corpora for factual, domain-specific responses. Modern RAG pipelines use hierarchical navigable small world (HNSW) vector databases for efficient similarity search. When a user requests data deletion, the systems typically only mark the record as deleted, leaving the embedding on disk physically unchanged. This soft-delete operation raises compliance concerns under data-erasure and retention requirements such as GDPR Article 17 and HIPAA. Analysis on three HNSW implementations confirms that deleted vectors remain physically recoverable by accessing the raw index files at the storage layer, bypassing API access. Using the Vec2Text inversion model without domain-specific fine-tuning, we show this vulnerability on multiple real-world datasets and data modalities. On Wikipedia...
论文介绍 研究发现HNSW向量数据库中软删除的嵌入向量仍可物理恢复，通过访问原始索引文件绕过API。使用Vec2Text逆向模型在多个数据集上展示漏洞，这对数据删除合规如GDPR构成挑战。强调需要更彻底的删除机制。
第一作者: Rumaisa Habib · 方向: 网络安全
审查规避机场代理网络测量用户调查中国
Abstract:In China, a burgeoning underground market sells citizens subscription-based censorship circumvention proxies known as ''airports''. We present the first systematic study of this ecosystem, combining user surveys, social media analysis, and active network measurements. We find that airports are by far the most popular off-the-shelf censorship circumvention tool in China, used by over half of our 1,667~survey respondents, who cite their ease of use, performance, and access to geo-restricted services like ChatGPT and Netflix. By scanning the Internet and scraping Telegram announcement channels, we identify 3,431 active airports built on a handful of open-source toolkits. We subscribe to 35 airports and characterize their performance, which often surpasses direct connections through the Great Firewall due to a distinctive multi-hop architecture. However, airports also pose new...
论文介绍 本研究系统分析了中国“机场”审查规避生态系统，通过用户调查、社交媒体分析和网络测量。发现“机场”是最流行的工具，性能优异但带来新风险。识别了数千个活跃机场，并评估其架构和性能，为理解审查规避提供全面视角。
第一作者: Polina Kozyreva · 方向: 密码学协议
大语言模型合规性测试PKCS#1密码学协议测试
Abstract:Testing implementations of binary protocols for specification compliance requires inputs that satisfy both structural and semantic constraints. Purely random generation and primitive mutations are often insufficient for exploring semantically meaningful behaviors in protocols that rely on Type-Length-Value (TLV) encoding, yet domain-specific compliance testing tools require deep protocol expertise and significant manual effort to construct. This work investigates whether grammar-level mutation combined with LLM-based code synthesis can serve as a viable, more generalizable approach to specification compliance testing. We evaluate the approach on PKCS#1 v1.5 signature verification -- a widely deployed TLV-encoded standard with a formally verified testing oracle (Morpheus) -- across 48 cryptographic library implementations. We reproduced 10 of 13 non-trivial specification...
论文介绍 该工作探究使用语法级突变结合LLM代码合成进行密码协议合规性测试。在PKCS#1 v1.5签名验证上评估，跨越48个密码库实现。结果表明，该方法能复现已知规格问题，为自动化测试提供更通用的途径。
第一作者: Yuchuan Tian · 方向: 软件安全
工具使用代理安全基准攻击分类LLM安全沙箱测试
Abstract:Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects. Existing evaluations often collapse these stages into a single attack success rate, making it difficult to tell whether a model merely agreed with an attacker or actually produced observable harm. We introduce SafeClawBench, a staged benchmark for tool-using agent security with 600 controlled adversarial tasks across six attack families: direct and indirect prompt injection, tool-return injection, memory poisoning, memory extraction, and ambiguity-driven unsafe inference. SafeClawBench reports three separate endpoints: semantic attack acceptance, audit-visible harm evidence, and sandbox-observed tool/state harm. Evaluating five agent endpoints under four...
论文介绍 SafeClawBench是一个分阶段基准，用于评估工具使用LLM代理的安全性，包含600个对抗任务和六个攻击家族。它分离语义攻击接受、审计可见危害证据和沙箱观测危害，提供更细粒度的安全评估，帮助区分模型响应和实际危害。
第一作者: Raj Patel · 方向: 系统安全
企业入侵响应多智能体框架结构化计划MITRE ATT&CK监督验证
Abstract:Enterprise intrusion response still depends on static playbooks and analyst-driven triage, creating delay between alert generation and containment. We present Agentra, a supervisable multi-agent Intrusion Response System (IRS) framework that converts alerts from IDS, EDR, and XDR platforms into structured incident response plans grounded in MITRE ATT&CK, MITRE D3FEND, and NIST CSF 2.0. Agentra decomposes response reasoning across role-scoped agents, validates proposed plans through a bounded Planner--Validator review loop, screens retrieved threat intelligence through a Moderator security gateway, gates actions through an Action Catalog and risk score, and records decisions in an append-only audit log. We evaluate Agentra against a static OASIS CACAO v2.0 cyber-playbook baseline on a 120-event corpus drawn from ThreatHunter-Playbook, Splunk BOTSv3, and DARPA OpTC. The...
论文介绍 企业入侵响应依赖静态剧本和人工分析，导致警报到遏制延迟。Agentra是一个可监督的多智能体框架，将IDS、EDR等平台的警报转换为基于MITRE ATT&CK、NIST CSF的结构化响应计划。它通过角色分解、验证循环和审计日志确保安全和可追溯，可提升企业安全事件自动化响应速度和准确性。
第一作者: Sidnei Barbieri · 方向: 密码学协议
网络安全文献可重复语料库元数据管理版本化快照学术API
Abstract:Cybersecurity literature reviews require a reproducible denominator: the set of papers that a protocol includes before screening and synthesis begin. Today, that denominator is often reconstructed from publisher portals, bibliographic indices, and scholarly application programming interfaces (APIs) whose coverage, formats, and query semantics change over time. This paper presents TopVenues, an open-source system that materializes corpus construction as a versioned research artifact. TopVenues declares a venue and year scope, uses DBLP Computer Science Bibliography (DBLP) as the metadata spine, enriches records with abstracts and BibTeX entries via open scholarly APIs and publisher-specific extractors, and stores the results in a monotonic SQLite snapshot, accessible via a command-line interface (CLI), a web interface, and export paths for review workflows. The May 2026...
论文介绍 网络安全文献综述需要可重复的论文集合，但现有来源如学术API易变。TopVenues是一个开源系统，基于DBLP元数据，集成开放API提供抽象和BibTeX，存储为版本化SQLite快照，支持命令行、网页和导出接口。它使语料库构建成为版本化研究工件，提高综述研究的可重复性和效率。
第一作者: William Kalikman · 方向: 隐私保护
联邦学习梯度反演攻击Transformer模型隐私保护嵌入子空间优化
Abstract:Federated learning allows multiple clients to jointly train a shared model by sending gradient updates to a central server while keeping raw inputs local. However, prior gradient inversion attacks show that these updates can reveal enough information to reconstruct client inputs. Existing attacks on transformers either optimize dummy inputs to match the true client updates, which is costly and unstable for modern models, or exploit the low rank of attention gradients to identify a subspace containing the true layer embeddings, followed by a discrete membership test for candidate tokens. However, this token test is brittle under numerical noise, i.e., from quantization or Differential Privacy (DP), and scales poorly for encoder models with non-causal attention. We introduce TIGER, a continuous gradient inversion attack that turns this subspace signal into a differentiable...
论文介绍 联邦学习中梯度更新可能泄露客户端输入隐私。现有梯度反演攻击针对Transformer模型时成本高或不稳定。TIGER提出连续梯度反演攻击方法，通过嵌入子空间距离优化实现可微分攻击，提高在数值噪声下的鲁棒性和可扩展性，用于评估联邦学习隐私风险。
第一作者: Xinru Liu · 方向: AI 安全
检索增强生成系统知识注入攻击冲突感知编辑模型中心攻击AI安全
Abstract:Injecting malicious knowledge into retrieval-augmented generation (RAG) systems can manipulate retrieved evidence and mislead downstream generation, posing a serious security threat for AI applications. Existing RAG injection attacks mainly rely on manipulating external knowledge bases, such as crafting malicious corpus. However, the synthetic text crafted by such data-centric methods could be detectable, leading to the failure of attacks. Beyond corpus manipulation, open-source retrievers are increasingly exposing RAG systems to model-centric attacks. In this paper, we propose conflict-aware retriever editing, i.e., CAREATTACK, a model-centric retriever attack framework for malicious knowledge injection in RAG. Specifically, CAREATTACK consists two stages of conflict-aware retriever editing and attack-preserving anchor repair. Conflict-aware retriever editing adapts efficient...
论文介绍 检索增强生成系统易受恶意知识注入攻击，现有方法依赖外部知识库操纵，可能被检测。CAREATTACK提出模型中心的攻击框架，通过冲突感知的检索器编辑和锚点修复，直接修改开源检索器模型以注入恶意知识，避开检测，用于评估RAG系统安全性。
第一作者: Yuecheng Wang · 方向: 软件安全
内存安全时间安全CHERI架构对象标识硬件扩展
Abstract:We propose CHERI-D, an architectural extension to CHERI that supports efficient temporal memory safety. Efficient memory safety is an increasing priority for programming languages, operating systems, and hardware designs, and CHERI is a leading hardware/software system that provides native spatial safety and a foundation for temporal memory safety. Due to CHERI lacking intrinsic architectural support for temporal memory safety, the state-of-the-art CHERI temporal safety solution, Cornucopia Reloaded, is a software-based solution that provides use-after-reallocation (UAR) protections instead of the stronger use-after-free (UAF) mitigation, and suffers performance overhead due to delayed reallocation and revocation. CHERI-D associates object identification (ID) metadata with capability pointers to provide temporal integrity of allocations. CHERI spatial safety allows CHERI-D to...
论文介绍 CHERI提供空间内存安全但缺乏时间安全支持，现有软件方案如Cornucopia有性能开销。CHERI-D通过关联对象标识元数据与能力指针，利用CHERI空间安全实现高效的时间完整性，防止使用后释放漏洞，增强硬件级内存安全效率。
第一作者: Amos Brocco · 方向: AI 安全
无冲突复制数据类型拜占庭容错确定性状态重建分布式一致性JSON文档
Abstract:Conflict-free Replicated Data Types (CRDTs) ensure Strong Eventual Consistency without coordination, but typically assume benign participants and rely on validation or exclusion to handle Byzantine behavior. We address this problem through deterministic state reconstruction: rather than deciding which updates are admissible, all accepted updates are incorporated, while only a subset contributes to the reconstructed state. We instantiate this approach in Melda, a non-intrusive delta-state CRDT for JSON documents, and show that its reconstruction model guarantees convergence even under arbitrary update injection: adversarial updates are either structurally rejected or treated as inputs to the reconstruction process. We formalize this model and prove that replicas deriving state from the same set of updates cannot diverge despite equivocation, omission, or message reordering. We...
论文介绍 无冲突复制数据类型通常假设良性环境，处理拜占庭行为困难。本文提出确定性状态重建方法，将所有更新纳入但重建子集以保证收敛。Melda作为JSON文档的CRDT实例，证明即使在对抗更新下也能保持一致性，增强分布式系统安全。
第一作者: Lenny Fukshansky · 方向: 密码学协议
格理论密码学无线通信安全应用数学结构
Abstract:Euclidean lattices are an interesting object of study in many regards and can have a rich structure arising from various constructions, e.g., from number field extensions. A particularly interesting class is the one of well-rounded lattices, as they relate to the well-known densest sphere packing problem in geometry, theta function minimization, and the famous Minkowski and Woods conjectures. In addition to being an important mathematical object in their own right, lattices also play a central role in many applications. This paper offers a survey of structured lattices and discusses their recent applications in lattice-based cryptography and secure wireless communications. Our goal is to spark the interest of mathematicians and adjacent communities in these fascinating topics in the intersection of lattices, number theory, cryptography, and wireless communications.
论文介绍 欧几里得格具有丰富结构，如well-rounded格，与球体填充和数论相关。本文综述结构化格及其在基于格的密码学和安全无线通信中的应用，旨在促进数学家和相关社区对这些跨学科话题的兴趣。
第一作者: Yibin Hu · 方向: 安全研究
世界模型数据投毒攻击模型操纵规划系统安全研究
Abstract:Model-based learning agents use learned world models to predict future states, plan actions, and adapt to new environments. However, the process of updating world models from collected experience creates a training-time attack surface: adversarially poisoned fine-tuning trajectories can manipulate the learned dynamics and thereby corrupt downstream planning. In this paper, we propose SWAAP, the first two-stage data poisoning framework for learned world models. In the first stage, SWAAP identifies a harmful target world model that induces low-return behavior under planning while remaining close to clean dynamics, using first-order bilevel optimization enabled by a transition-gradient theorem. In the second stage, SWAAP realizes this target through stealth-constrained gradient matching, modifying only a limited fraction of fine-tuning transition targets so that the induced...
论文介绍 基于模型的学习代理使用世界模型进行规划，但训练数据可能被投毒操纵。SWAAP提出两阶段数据投毒框架：先通过双层优化识别有害目标世界模型，再通过隐蔽约束梯度匹配实现投毒，以低回报行为腐蚀规划，揭示智能体训练漏洞。
第一作者: Ngela Landon Ntung · 方向: AI 安全
人脸活体检测架构偏见视觉Transformer卷积神经网络公平性
Abstract:Face Presentation Attack Detection (PAD) systems constitute a critical security layer in biometric authentication; however, existing approaches exhibit systematic performance disparities across demographic groups, disproportionately affecting individuals with darker skin tones. This paper presents a comparative empirical investigation of whether Vision Transformer architectures reduce demographic bias in face PAD systems relative to convolutional baselines. Experiments are conducted on the CASIA-SURF Cross-Ethnicity Face Anti-Spoofing (CeFA) dataset. Three architectures are evaluated: a Multimodal ViT-Tiny trained from scratch, a ResNet18 CNN baseline, and a pretrained DeiT-S fine-tuned on CeFA across African, East Asian, and zero-shot Central Asian demographic groups. DeiT-S achieves the highest overall accuracy of 97.27% and the lowest EER of 0.86%, outperforming ResNet18 at...
论文介绍 针对人脸活体检测（PAD）系统在不同人群中存在性能差异的问题，本文比较了视觉Transformer（ViT）与卷积神经网络（CNN）架构能否减轻此类偏见。研究在跨种族数据集CeFA上进行，评估了从零开始训练的多模态ViT-Tiny、ResNet18基线以及预训练的DeiT-S。结果表明，预训练的DeiT-S模型在总体准确率和等错误率上均表现最佳，表明其架构特性有助于提升检测的公平性与鲁棒性。
第一作者: Chih-Duo Hong · 方向: 密码学协议
大语言模型水印检测签名过滤查询效率
Abstract:Statistical watermarks help organizations attribute large language model (LLM) outputs, yet existing detectors often struggle when watermark signals are weak, texts are repetitive, or watermarks are edited. We propose signature filtering, a detection-time module that enhances watermark detection without modifying watermark embedding and text generation. It learns a small set of ``signature'' tokens whose presence makes watermark tests unreliable, and removes these tokens before detection. The signatures are obtained by solving a mixed-integer linear program on a small training set, with constraints that maximize the true positive rate. We additionally derive finite-sample and asymptotic bounds under several attacker models (color-blind, color-adaptive, and distributionally correlated). On four well-known watermark families (Kgw, Sweet, Unigram, Exp), four benchmark corpora...
论文介绍 统计水印用于归属大语言模型输出，但现有检测器在信号弱、文本重复或水印被编辑时效果不佳。本文提出「签名过滤」模块，通过在检测前移除一组经过学习的、可能干扰检测结果的「签名」令牌，来增强检测的可靠性。该方法通过在一个小型训练集上求解混合整数线性规划来获得签名，旨在最大化真阳性率。实验在多种水印方法和基准语料库上验证了其有效性，为改进水印检测提供了轻量级方案。
第一作者: Kunal Jain · 方向: 系统安全
模型安全GPU内存布局模型窃取混淆
Abstract:Large foundation models deployed on third-party and shared accelerator infrastructure face a practical risk of model exfiltration that existing defenses do not fully address. In common serving deployments, model providers control the VM or bare-metal serving stack but not the surrounding hardware substrate. The host to GPU interconnect, accelerator fabric, and neighboring infrastructure components remain outside the tenant's trust boundary and have been shown to be exploitable. Hermes demonstrates lossless DNN reconstruction from passive PCIe observation, while TunnelS exfiltrates HBM contents at high throughput via driver-level access without disrupting inference. Co-tenant VMs can further access memory-mapped interfaces or misconfigured RDMA regions without physical co-location. These attacks exploit a common property of ML systems: model weights are stored in large...
论文介绍 部署在第三方共享基础设施上的大模型面临模型窃取风险，现有防御未能完全解决。攻击者可利用模型权重存储在连续内存区域这一特性，通过PCIe观测或驱动级访问等方式重建模型。本文提出「CloakLM」系统，通过混淆模型参数在GPU显存中的存储布局来应对此类威胁。该系统旨在破坏模型内存的连续性，增加攻击者从硬件层面被动或主动重建模型的难度，为模型服务阶段的安全提供了新的防护思路。
第一作者: Pedram MohajerAnsari · 方向: 软件安全
对抗性补丁黑盒攻击目标检测查询效率
Abstract:Adversarial patches pose a practical threat to modern object detectors. Prior work shows vulnerability, but three gaps limit actionable insight: (i) few \emph{score-based black-box} attacks \emph{jointly} optimize patch \emph{location, texture, and size} under tight query budgets; (ii) success is rarely tied to the patch's \emph{visual footprint}; and (iii) evaluations often conflate EOT robustness with plain-view suppression. We present \method{}, a query-efficient, budget-adaptive black-box attack that couples a lightweight \emph{Contextual Thompson-Sampling} placer with NES-style pixel updates, growing the patch only when progress stalls. Reporting is anchored by a \emph{strict plain-image} suppression test; EOT is audited but never used as a substitute for success, and optional appearance/printability weights expose strength--visibility trade-offs. Across YOLOv5, Faster...
论文介绍 对抗性补丁对目标检测器构成实际威胁，但现有研究存在空白。本文提出「Budget-Aware Adaptive Adversarial Patches」方法，这是一种查询高效的黑盒攻击。该方法结合了一个轻量级的「上下文汤普森采样」放置器与NES风格的像素更新策略，并仅在进展停滞时才扩大补丁尺寸。研究通过严格的纯图像抑制测试来评估成功与否，并分析了攻击强度与补丁可见性之间的权衡，为理解针对目标检测器的物理世界攻击提供了新见解。
第一作者: Jisoo Kim · 方向: 机器人操作 · 来源: cs.RO
灵巧操作视觉语言模型零样本学习3D关键点
Abstract:We present a zero-shot framework for long-horizon dexterous manipulation that grounds language instructions into executable 3D task plans from calibrated multi-view RGB images. Rather than training an end-to-end policy, our system uses a vision-language model (VLM) to produce reference-frame task grounding and primitive-level 2D keypoints, then lifts them into 3D via multi-view fusion. This lifting combines triangulation of view-wise VLM groundings with reference-view ray voting, which searches along a semantic camera ray for geometrically consistent candidates across neighboring views. The resulting 3D keypoints support both pick-and-place and tool-use: for tool-use, we retrieve an object-centric atomic action corresponding to the inferred skill category and align its stored 6D tool trajectory to the scene; for dexterous execution, we expand the lifted grasp keypoint into a...
论文介绍 本文提出一个用于长时程灵巧操作的零样本框架，能将语言指令转化为可执行的3D任务规划。系统利用视觉语言模型（VLM）从多视角RGB图像中生成参考系下的任务定位和2D关键点，再通过多视角融合将其提升至3D空间。该方法结合了视图间VLM定位的三角测量与参考视图射线投票，以寻找几何一致的候选点。所得3D关键点支持抓取放置和工具使用操作，无需针对具体任务进行策略训练，展示了VLM在机器人操作中的强大推理能力。
第一作者: Bhawna Paliwal · 方向: 机器人操作 · 来源: cs.RO
灵巧操作数据生成视频模仿学习人机迁移
Abstract:How can we scalably generate data for robotic manipulation, especially on human-like platforms such as dexterous multi-fingered hands? Learning from human videos has recently emerged as a likely answer to this question. However, difficulties in estimating hand-object interaction and crossing the human-to-robot embodiment gap have hindered the adoption of abundant monocular RGB-only human videos as the primary source of robot manipulation data. In this work, we present DO AS I DO, an algorithm to reconstruct and retarget monocular RGB human videos to multi-fingered dexterous robotic hands. DO AS I DO reconstructs hand-object interactions from various egocentric and exocentric in-the-wild video sources. The algorithm then retargets these hand-object interaction estimates into a sequence of actions executable in the real world, yielding robot-complete manipulation data from...
论文介绍 为机器人操作，特别是灵巧手，生成大规模数据是一个挑战。本文提出「DO AS I DO」算法，旨在从单目RGB人类视频中重建并重定向手-物交互，为多指灵巧机器人手生成可执行的操作数据。该方法能从各种视角的真实视频中重建交互，并将其重定向为可在真实世界执行的动作序列。这为利用海量人类视频数据跨越人-机器人具身差距、为灵巧操作提供训练数据提供了可行路径，有望降低机器人学习的数据采集成本。
第一作者: Madhav Rijal · 方向: 机器人操作 · 来源: cs.RO
农业机器人分支操作参数估计有限元方法
Abstract:This study presents a method for modeling diverse plant branches by iteratively estimating material parameters to support delicate branch manipulation. Branch manipulation is necessary in agricultural robotics for plant repositioning, stabilizing, and clearing visual obstructions in dense foliage. The proposed method builds a tetrahedral branch model from point-cloud data and simulates its behavior using the finite element method. Using real observed deformation data, it iteratively estimates branch parameters and then computes an optimal path with a deformation-aware motion planner to move and stabilize branches within another robot's field of view. Across 30 trials on branches with varying geometries and material properties, the proposed method reduced the deformation energy by 35.69% while increasing the path length by 8.10% on average.
论文介绍 农业机器人需要对植物分支进行操作，例如移动、固定或清理。本文提出一种通过迭代参数估计来建模多样化植物分支的方法，以支持此类精细操作。该方法首先从点云数据构建分支的四面体模型，并使用有限元方法模拟其行为。然后，基于实际观测到的形变数据，迭代估计分支的材料参数。最后，利用感知到的形变规划最优路径，以在另一机器人视野内移动和固定分支，实验表明该方法能有效降低操作中的形变能。
第一作者: H. M. Sabbir Ahmad · 方向: 多模态具身 · 来源: cs.RO
自动驾驶混合现实硬件在环测试平台
Abstract:We propose a mixed-reality, hardware-in-the-loop (HIL) testbed for autonomous vehicles that seamlessly integrates a physical testbed of mobile robots with a high-fidelity simulation environment. The virtual simulation enables the creation of diverse, safety-critical driving scenarios to validate state-of-the-art perception, planning, and control algorithms, while augmenting simulations with physical robots equipped with multimodal sensors in photorealistic virtual environments further facilitating rigorous validation. Our testbed also features vehicular connectivity using wireless communication and can accommodate a large number of agents through the combination of physical robots and virtual simulated agents, supporting research on multi-agent systems including Connected and Autonomous Vehicles (CAVs). Finally, we present a safety-guaranteed framework combining perception...
论文介绍 本文提出一个用于自动驾驶车辆的混合现实硬件在环测试平台，将物理移动机器人与高保真仿真环境无缝集成。虚拟仿真可用于创建多样化的安全关键驾驶场景以验证感知、规划和控制算法，同时物理机器人及其多模态传感器被置于逼真的虚拟环境中，增强了验证的严格性。该平台支持无线通信连接，并能通过物理与虚拟智能体的结合容纳大量智能体，可用于研究包括网联自动驾驶车辆在内的多智能体系统，为算法验证提供了灵活且安全的测试环境。
第一作者: Amber K. Rothe · 方向: 具身智能 · 来源: cs.RO
连续体机器人形状感知直接激光写入应变传感器单片集成
Abstract:Continuum robots offer a promising approach for minimally invasive and natural-orifice surgical procedures due to their inherent compliance and dexterity. However, this flexibility also makes estimating the current shape of the robot challenging. Several approaches have been used to reconstruct the shape of these robots, including imaging, optical sensing, magnetic sensing, and resistive sensing. Strain sensors fabricated using direct laser writing (DLW) could provide an alternative sensing method. This technique involves using a laser to induce carbonization of certain polymers to create graphene patterns, such as strain sensors. In this paper, we demonstrate how a flexible continuum joint and a DLW sensor can be machined as one monolithic structure using the same laser and the same setup. The fabricated sensors are characterized using linear and nonlinear models, which are...
论文介绍 该研究针对连续体机器人形状感知的挑战，提出一种利用直接激光写入技术在柔性连续体关节上原位制造碳化应变传感器的方法。该技术将柔性关节与传感器作为单片结构在同一激光系统下加工，简化了制造流程。论文对制造的传感器进行了线性与非线性模型表征，旨在为微创手术等应用提供一种新型、集成的形状感知方案。
第一作者: Thomas M. Kwok · 方向: 模仿学习 · 来源: cs.RO
机器人遥操作深度估计运动学校正遮挡RGB-D相机
Abstract:Markerless, single-RGB-D-camera motion capture provides a low-cost and non-invasive alternative to conventional marker-based systems for robot teleoperation; however, depth estimation often degrades in the presence of self-occlusion, particularly during upper-limb motion. This paper presents an Arm Kinematic Correction (AKC) method that improves depth estimation by enforcing geometric constraints based on constant arm lengths. The proposed approach reconstructs occluded joint depths by leveraging wrist positions and predefined arm lengths via a deterministic formulation based on the Pythagorean theorem, thereby avoiding the need for complex probabilistic modeling or parameter tuning. Experimental validation against a Vicon reference system demonstrates reliable performance for both static and dynamic joint motions, evaluated using root-mean-square error (RMSE) and Pearson...
论文介绍 针对使用单RGB-D相机进行无标记点遥操作时，因自遮挡导致深度估计退化的问题，本文提出一种确定性的手臂运动学校正方法。该方法基于恒定臂长的几何约束，利用手腕位置和勾股定理重构被遮挡关节的深度，避免了复杂的概率模型。实验表明该方法在静态和动态任务中均能可靠提升深度估计精度，为低成本遥操作提供了实用解决方案。
第一作者: Yue Qin · 方向: 机器人操作 · 来源: cs.RO
轮足双足机器人分层控制物体滑动腿式操作非线性模型预测控制
Abstract:In this letter, we present a hierarchical control framework that enables wheeled bipedal robots to perform planar object sliding tasks with their wheeled legs. The proposed approach formulates a nonlinear model predictive controller (NMPC) based on a reduced-order three rigid bodies (TRB) dynamical model that explicitly accounts for the hip roll degree of freedom and multiple wheel-environment contact modes, which is essential for lateral stepping and pedipulation tasks. Within this framework, the NMPC simultaneously regulates robot locomotion and interaction forces, allowing the robot to stably execute both rolling and object manipulation behaviors. A trajectory-optimization-based robot-object motion planner is developed to generate reference motions that incorporate stick-slip transitions in ground-object contact. Two representative pedipulation motions, namely scooting and...
论文介绍 本文提出一种分层控制框架，使轮足双足机器人能够利用其轮式腿部执行平面物体滑动任务。核心方法基于一个考虑髋关节滚动自由度和多轮地接触模式的三刚体动力学模型，采用非线性模型预测控制器同步协调机器人的移动和操作。该框架通过轨迹优化规划器生成包含粘滑过渡的参考动作，实现了机器人稳定移动与物体操作的结合。
第一作者: Yu Zhang · 方向: 机器人操作 · 来源: cs.RO
机器人操作流匹配可逆神经网络一步去噪多模态观测
Abstract:This paper presents an invertible neural network adapter for general robotic manipulation, designed to generate precise high-dimensional actions conditioned on multimodal observations, including visual, linguistic, and proprioceptive inputs, through a one-step denoising process. Built upon a flow-matching formulation, the proposed adapter effectively constrains the action generation trajectory within an invertible latent space, thereby enabling efficient and high-quality dexterous action synthesis with only a single inference step. Compared with conventional iterative flow-matching policies, the proposed framework substantially reduces inference complexity while maintaining strong action prediction accuracy and stability. Extensive experiments are conducted across a diverse set of simulation benchmarks and real-world robotic platforms to evaluate the effectiveness of the...
论文介绍 为解决高维动作生成问题，本文提出一种基于可逆神经网络的适配器，用于通用机器人操作。该方法构建在流匹配框架上，将动作生成约束在可逆隐空间中，使得模型仅需一次去噪推理步骤即可基于视觉、语言和本体感知等多模态输入生成精确动作。相比传统迭代策略，该方法显著降低了推理复杂度，同时保持了动作预测的准确性和稳定性。
第一作者: Zhiyu Chen · 方向: 具身智能 · 来源: cs.RO
状态估计多传感器融合LiDARGNSS退化场景
Abstract:Robust state estimation and mapping in long-term, large-scale, and highly dynamic environments remains a key challenge in robotics. Existing LiDAR-Inertial-Visual Odometry (LIVO) systems achieve strong local accuracy but suffer from accumulated drift over long distances and may fail in geometrically degraded or textureless scenes. Meanwhile, GNSS-aided fusion frameworks often rely on LiDAR or visual odometry for state prediction and outlier rejection, making them vulnerable when odometry degenerates. To address these limitations, we propose a tightly coupled LiDAR-Inertial-Visual-GNSS fusion framework based on an Error-State Iterated Kalman Filter. An online spatiotemporal alignment module using Dynamic Time Warping is introduced for highly dynamic conditions. To better exploit GNSS precision, we develop observation models based on Doppler shifts and fixed-anchor...
论文介绍 针对大尺度、高动态环境下现有LiDAR-视觉惯性里程计易累积漂移及在几何退化场景失效的问题，本文提出一种紧耦合的LiDAR-惯性-视觉-GNSS融合里程计系统。该系统基于误差状态迭代卡尔曼滤波器，引入动态时间规整模块应对高动态条件，并设计了基于多普勒频移和固定锚点的GNSS观测模型，以提升在里程计退化时的状态估计鲁棒性。
第一作者: Yuzhe Huang · 方向: 机器人操作 · 来源: cs.RO
触觉表示具身视觉灵巧手基准测试多模态学习
Abstract:Establishing a universal benchmark for tactile representation learning in robotic manipulation remains challenging due to the diversity of tactile sensor designs, data formats, and robot embodiments. Rather than seeking to establish such, we explore a scalable and promising direction for future development: egocentric vision paired with full-hand tactile data. To this end, we introduce \textbf{HT-Bench}, a large-scale multi-task benchmark for dexterous full-hand tactile sensing, comprising 10M RGB frames and 7.8M tactile frames collected across 226 tasks. HT-Bench evaluates tactile representations from three key perspectives: whether they encode meaningful contact geometry, whether they can align tactile observations with visual information, and whether they generalize to unseen tasks. To assess these capabilities, HT-Bench includes four tasks: fine-grained tactile similarity...
论文介绍 为推动触觉表示学习的发展，本文提出了一个大规模多任务基准HT-Bench。该基准包含超过1000万RGB帧和780万触觉帧，覆盖226个任务，专注于灵巧全手触觉感知。HT-Bench从接触几何编码、视觉-触觉对齐和任务泛化能力三个角度评估触觉表示，并配套提供了基准学习方法，旨在探索具身视觉与全手触觉数据结合这一有前景的研究方向。
第一作者: Vladimír Kubelka · 方向: 导航与运动 · 来源: cs.RO
森林场景多传感器数据集4D成像雷达语义分割机器人感知
Abstract:Autonomous robots operating under forest canopies need robust perception of trees and surrounding vegetation across varying seasonal conditions. Existing forestry datasets provide lidar or camera data with per-tree annotations, but none include co-registered 4D imaging radar -- a modality of growing interest for its resilience to visual degradation, surface contamination, and vegetation occlusion. We introduce a multi-sensor forest dataset collected by a mobile robot equipped with a high-resolution FMCW imaging radar, lidar, RGB camera, IMU, and RTK-GNSS. The site was recorded in two sessions under contrasting vegetation states, and 3D cuboid annotations -- including per-tree diameter estimates -- provide shared semantic labels across all three perception modalities. Furthermore, we provide baseline results for semantic segmentation of the radar and lidar point clouds using...
论文介绍 为提升机器人在森林林冠下的环境感知能力，本文引入了一个名为Viking Hill的多传感器森林场景数据集。该数据集由移动机器人在不同季节条件下采集，包含高分辨率FMCW成像雷达、激光雷达、RGB相机等传感器的同步数据，并为所有模态提供了带有树木直径估计的3D立方体标注。数据集旨在推动对视觉退化、表面污染及植被遮挡具有鲁棒性的雷达感知算法研究。
第一作者: Yukai Ma · 方向: 导航与运动 · 来源: cs.RO
单目感知3D占据预测人行道机器人混合学习导航
Abstract:Sidewalks in the real world are crowded, cluttered, and less structured than roads, making 3D occupancy prediction a key ingredient for the safe navigation of mobile robots such as delivery bots and electric wheelchairs. Existing occupancy learning pipelines are largely designed for on-road autonomous driving and often train on large-scale paired LiDAR-RGB datasets with dense 3D supervision and multiple camera inputs, which are costly to collect and do not adequately capture sidewalk-specific characteristics. We propose WalkOCC, a hybrid Ray-marching monocular 3D occupancy perception framework for robots operating on sidewalks. WalkOCC explicitly couples geometric grounding from LiDAR-RGB paired data with scalable learning from large-scale unpaired monocular images. It bootstraps pseudo occupancy supervision from paired sequences and jointly learns image-level representations...
论文介绍 针对人行道场景拥挤杂乱、缺乏结构的特点，本文提出WalkOCC框架，用于机器人单目3D占据感知。该框架结合LiDAR-RGB配对数据的几何监督与大规模无配对单目图像的可扩展学习，通过光射线行进方法将两者耦合。它从配对序列中自举生成伪占据监督，从而在仅依赖单目输入的情况下，学习有效的3D占据表示，以支持人行道机器人的安全导航。
第一作者: Alessandro Scherl · 方向: 具身智能 · 来源: cs.RO
视觉伺服Vision Transformer自适应分辨率平铺特征粒度具身智能
Abstract:Visual servoing with self-supervised Vision Transformer (ViT) features enables training-free robotic positioning with strong generalization, but faces a fundamental trade-off between robustness and precision. Coarse patch-level descriptors provide stable correspondences yet limit positioning accuracy. Increasing image resolution improves precision but yields only marginal robustness gains - under perturbation, high-resolution processing improves convergence success rate from 76.6% to just 81.0% despite 12x more ViT patches. Therefore, we propose Adaptive Resolution Tiling Visual Servoing (ART-VS), a two-phase method that adapts feature granularity to servoing progress: a coarse phase at native ViT resolution for stable alignment, then a tiled high-resolution phase that restricts matching to local neighborhoods improving positioning accuracy. Without any task-specific training...
论文介绍 该研究针对视觉伺服中鲁棒性与精度之间的根本权衡，提出自适应分辨率平铺视觉伺服方法。ART-VS采用两阶段策略：首先在原始分辨率下进行粗对齐以确保稳定性，然后切换到高分辨率平铺阶段，在局部邻域内进行匹配以提高定位精度。该方法无需任务特定训练，可应用于具身智能中的机器人定位任务。
第一作者: Simon Schwaiger · 方向: 机器人操作 · 来源: cs.RO
视觉语言模型空间一致性机器人操作特征重构语言条件任务
Abstract:Vision-Language Models (VLMs) enable robots to follow open-language instructions. However, dense VLM embeddings have shown to be noisy and lack spatial consistency. This is problematic for robotic applications, which require simultaneous reasoning over semantics and 3D space. We examine spatial structure across recent VLMs and propose ReSiReg, a feature reconstruction method that uses spatially consistent VLM intermediates to improve dense language-grounded retrieval. ReSiReg clusters intermediates into visual prototypes, derives their language descriptors, and reconstructs each patch as a soft mixture of prototype-level language embeddings. We evaluate quantitatively on OVSS and 3D mapping across backbones, and qualitatively in real-world manipulation scenes. Quantitative results show improved dense retrieval; manipulation scenes show more spatially consistent target...
论文介绍 该研究针对视觉语言模型在机器人任务中密集嵌入噪声大且缺乏空间一致性的问题，提出ReSiReg特征重构方法。该方法利用VLM空间一致的中间特征，聚类为视觉原型并派生语言描述，将每个像素块重构为原型级语言嵌入的软混合。实验表明，在OVSS和3D映射任务中提高了密集检索性能，并在真实世界操作场景中展现出更一致的目标定位。
第一作者: Roberto Corlito · 方向: 导航与运动 · 来源: cs.RO
多模态SLAM四足机器人传感器配置同时定位与地图构建腿部运动
Abstract:Autonomous navigation of quadrupedal robots in diverse environments fundamentally relies on resilient Simultaneous Localization and Mapping (SLAM). While visual-inertial SLAM has matured across wheeled, handheld, and aerial platforms, a critical evaluation gap remains regarding how hardware-level sensor configurations affect performance under the aggressive dynamics of legged locomotion. Quadrupeds introduce distinct embodiment-induced sensory challenges, including foot-impact shocks, high-frequency mechanical vibrations, and rapid angular rotations, which degrade standard perception pipelines. To address this gap, we present a systematic evaluation of state-of-the-art visual, visual-inertial, and LiDAR-visual-inertial SLAM methods using the GrandTour dataset recorded on an ANYmal D quadruped. We isolate and quantify the impacts of camera modalities, shutter techniques, and...
论文介绍 该研究针对四足机器人上多模态SLAM的性能评估缺口，系统探讨了传感器配置对同时定位与地图构建的影响。利用ANYmal D四足机器人记录的GrandTour数据集，比较了视觉、视觉惯性和LiDAR-视觉惯性SLAM方法，量化了相机模态、快门技术等因素在腿部运动挑战下的表现。研究结果为优化四足机器人SLAM系统提供了实证依据。
第一作者: Stefano Bernagozzi · 方向: 具身智能 · 来源: cs.RO
巡逻规划拥挤环境人群感知概率模型马尔可夫决策过程
Abstract:Autonomous mobile service robots are often required to complete tours that require navigating through a set of locations in an environment. Example domains include guiding people through a shopping mall, delivering packages in a fulfilment centre, or giving guided tours in a museum. However, in crowded environments, the presence of people may negatively impact robot performance. For example, humans will activate robot collision avoidance manoeuvres that slow the robot down. Crowds move stochastically and vary throughout the day. In this paper we present a probabilistic tour planner for crowded environments which explicitly reasons over human congestion. We learn circular linear flow field (CLiFF) maps which predict human trajectories given an initial observation. We then use these predictions to build and solve a Markov decision process online which efficiently routes the...
论文介绍 该研究关注拥挤环境中机器人的巡逻规划问题，其中人群存在会降低机器人性能。提出一种概率规划器，通过学习循环线性流场地图来预测人群轨迹，并在线构建马尔可夫决策过程，根据预测进行高效路由。该方法适用于购物中心引导、仓库配送等场景，能够自适应人群变化，优化机器人路径。
第一作者: Arunim Joarder · 方向: 机器人操作 · 来源: cs.RO
触觉传感模拟到现实迁移表示学习共享潜空间多模态对齐
Abstract:Tactile sensing provides direct measurements of contact interactions that are essential for robotic manipulation. However, current simulators lack the fidelity to faithfully model the complex deformation and transduction mechanics of tactile sensors, severely hindering sim-to-real transfer in robot learning pipelines. To address this challenge, we propose a multi-modal representation learning framework that aligns heterogeneous tactile modalities within a shared latent space, eliminating the need for accurate raw-signal simulation while preserving relevant contact information. Our approach employs modality-specific encoders to project diverse tactile observations, such as simulated penetration depth and real-world capacitance, into a common embedding space. The model is trained using self- and cross-reconstruction objectives alongside contrastive alignment, encouraging...
论文介绍 该研究针对触觉传感的模拟到现实迁移挑战，提出TactSpace框架。该方法通过多模态表示学习，将不同触觉模态（如模拟穿透深度和现实电容）对齐到共享潜空间，避免对原始信号精确模拟的需求。模型训练采用自重建、跨重建和对比对齐目标，保留相关接触信息。这有助于在机器人学习中实现触觉传感的有效迁移。
第一作者: Kinam Kim · 方向: VLA 通用模型 · 来源: cs.RO
视觉语言动作模型残差强化学习对象中心模拟到现实迁移零样本学习
Abstract:Vision-Language-Action (VLA) models can generalize across diverse manipulation tasks, but their imitation-learning-based policies remain brittle in precise physical interactions due to compounding execution errors; Can a reinforcement learning policy trained purely in simulation improve the robustness of real-world VLAs zero-shot? Residual RL, which learns a corrective policy on top of a frozen VLA, offers a natural framework, but existing approaches face a fundamental sim-to-real dilemma: privileged-state methods require lossy distillation for deployment; image-based methods suffer from the visual domain gap; and real-world RL is costly and unsafe. We propose an object-centric residual RL framework that refines VLA actions using object poses, enabling a compact observation space that transfers consistently between simulation and reality. To align the two domains, we...
论文介绍 该研究旨在提升视觉语言动作模型在精确操作中的鲁棒性。提出对象中心残差强化学习框架，在冻结的VLA之上学习纠正策略，使用对象姿态作为紧凑观察空间，实现在模拟和现实间的一致迁移。该方法通过域对齐技术解决模拟到现实困境，无需损失性蒸馏或处理视觉域差距，从而支持VLA的零样本现实增强。
第一作者: Nick B. Schroeder · 方向: 具身智能 · 来源: cs.RO
LiDAR聚类非重复传感器点云处理连续自适应聚类机器人导航
Abstract:Real-time LiDAR clustering identifies structures in point clouds, which is an essential prerequisite for many mobile robotics algorithms. Current methods are mostly developed for repetitive mechanical LiDAR sensors. Recently, the use of non-repetitive LiDAR sensors is strongly increasing due to their small cost and form factor. Such non-repetitive Risley prism-based sensors violate two key assumptions of repetitive mechanical sensors: structured scan lines and well-defined frame boundaries. Their Rhodonea-curve trajectories produce non-uniform point distributions, and the absence of a rotation cycle renders conventional scan line indexing inapplicable. To meet such new requirements, we developed C-ARC, a Continuous-Adaptive Range Clustering framework that maintains a persistent dual-graph over a sliding window, decoupling high-frequency point insertion from on-demand cluster...
论文介绍 该研究解决非重复LiDAR传感器在点云聚类中的挑战。传统方法依赖重复传感器的结构化扫描线和帧边界，而Risley棱镜传感器产生非均匀点分布且无旋转周期。C-ARC采用连续自适应范围聚类框架，在滑动窗口上维护持久双图，将高频点插入与按需聚类分离。这提高了对非重复传感器的适应性，适用于移动机器人导航等应用。
第一作者: Giovanni B. Dessy · 方向: 导航与运动 · 来源: cs.RO
四足机器人负载运输零力矩点阻抗控制模型预测控制
Abstract:Load transportation with quadruped robots is strongly affected by the dynamics of the physical interface between the robot and the load. Passive spring-based arms reduce weight and complexity compared to active manipulators, but their spring-damper dynamics can introduce oscillatory forces that degrade locomotion stability. This paper derives an extended Zero Moment Point (ZMP) formulation that includes passive payload-interface dynamics, relating stiffness, damping, and payload mass to the stability margin. The analysis shows that underdamped configurations can resonate with locomotion harmonics. Based on this insight, we augment a Single Rigid Body Dynamics model with passive subsystem dynamics and integrate it into a Model Predictive Control framework. In simulation, the proposed controller reduces stability violations by up to $10\times$, from $7.0\%$ to $0.7\%$, and...
论文介绍 该研究关注四足机器人负载运输的稳定性问题，其中被动弹簧臂的振荡动力学可能破坏运动。提出ZiMPedance方法，扩展零力矩点公式以包含被动接口动力学，分析参数对稳定性裕度的影响。基于此，将被动子系统集成到模型预测控制中，在仿真中显著减少稳定性违规。这有助于优化四足机器人的负载运输能力。
第一作者: Chris Lee · 方向: 策略学习 · 来源: cs.RO
机器人手势强化学习人类反馈大语言模型人机交互
Abstract:Expressive gestures are essential for natural and effective communication, complementing speech when verbal cues alone are insufficient (e.g., pointing). For social robots such as the humanoid Pepper, producing natural and expressive movements is critical for improving human-robot interaction (HRI) and long-term acceptance. However, generating gestures remains challenging due to reliance on expert-authored animations, resulting in rigid behaviors that are impractical for dynamic and diverse environments. Alternatively, machine learning approaches often struggle to capture perceived naturalness, becoming increasingly challenging with more degrees of freedom. Consequently, producing expressive robot gestures requires a system that can adapt to the environment while adhering to social norms and physical constraints. Recent advances in large language models (LLMs) enable dynamic...
论文介绍 本研究针对社交机器人手势生成问题，提出基于大语言模型的迭代强化学习方法。通过人类反馈优化手势表达，解决现有方法依赖专家动画或机器学习导致的自然性不足问题。该方法旨在生成适应动态环境的自然表达手势，应用于如Pepper的社交机器人，以改善人机交互效果和长期接受度。
第一作者: Trevor Exley · 方向: 具身智能 · 来源: cs.RO
软机器人晶格结构单元驱动分布式形态气动驱动
Abstract:Soft lattice structures are increasingly used in robotics to tailor compliance and guide deformation; however, actuation is typically introduced at the device or module level, with actuators inserted into otherwise passive architectures. In this work, we move actuator-lattice co-design to the unit-cell scale. We present an embedded pneumatic unit cell that integrates curved-strut lattice geometry with a bidirectional bellow actuator within a single monolithic element. When tessellated, the lattice functions as a distributed actuation field in which global morphology is governed by spatial actuation patterns rather than uniform pressurization. Experimental characterization of 1x1, 2x2, and 3x3 tessellations demonstrates scalable displacement and force generation with repeatable cyclic performance. Selective actuation of unit cells in a 3x3x3 array produces distinct global...
论文介绍 软晶格结构在机器人中用于定制柔顺性，但驱动通常局限于设备级。本文提出单元级别选择性驱动方案，设计嵌入式气动单元格，集成曲柄晶格和双向波纹管驱动器。当拼接时，晶格形成分布式驱动场，通过空间驱动模式控制全局形态。实验验证了从1x1到3x3拼接的可扩展性能，为软机器人形态控制提供新方法。
第一作者: Alexander Belyaev · 方向: 数据集与评测 · 来源: cs.RO
表面分类能量特征深度学习移动机器人数据集比较
Abstract:The energy-based method remains a comparatively underexamined approach for surface classification in mobile robotics, despite promising results in constrained environments. This study evaluated the viability of using energy-derived features as either a standalone classification modality or as supplementary input to inertial data. A comprehensive evaluation was conducted across three publicly available datasets, comparing the performance of modern deep learning architectures including recurrent neural networks, convolutional neural networks, encoder-only transformers, and Mamba state-space models, under automated hyperparameter tuning and input sequence length optimization. The models achieved higher accuracy than previously reported values on all evaluated datasets, with the convolutional neural network yielding the highest overall performance. When relying exclusively on...
论文介绍 能量特征方法在移动机器人表面分类中未被充分探索。本研究评估能量特征作为独立或补充模态的可行性，在三个公开数据集上比较多种深度学习架构，包括RNN、CNN、Transformer等。模型在自动超参数调优下达到更高精度，其中CNN性能最佳。该研究为环境感知应用提供数据支持，提升分类准确性。
第一作者: Haoqi Han · 方向: 导航与运动 · 来源: cs.RO
微机器人仿生腿高自由度轻量级运动学
Abstract:In microrobotics, enhancing locomotion capabilities by increasing the degrees of freedom (DoF) of leg mechanisms under severe spatial constraints remains a significant challenge. Inspired by insect locomotion, this paper presents a novel micro-scale parallel leg mechanism with four degrees of freedom, and systematically analyzes its mechanical design, electrical system, and kinematics. The design incorporates two spherical five-bar linkages to achieve spatial motion within a parallel four-bar configuration. Furthermore, a concentric design strategy is employed to simplify the analytical solution of the leg kinematics. Due to the parallel system architecture, all actuators are located on the main body, substantially reducing the equivalent inertia of moving parts compared to traditional high-DOF leg structures. The total mass of the system is only 18.9 g, with an end-effector...
论文介绍 微机器人中，在空间约束下增加腿自由度以增强运动能力是挑战。受昆虫启发，本文设计四自由度微型并联腿机构，采用两个球形五杆连杆实现空间运动，并使用同心设计简化运动学分析。系统质量仅18.9克，所有致动器位于主体，降低运动惯性，适用于小型机器人提升移动性能。
第一作者: Kui Yang · 方向: 机器人操作 · 来源: cs.RO
具身智能移动操作仿真转移平台自动场景生成
Abstract:Mobile manipulation is a fundamental capability in embodied intelligence robotics. The growing demand for robust and generalizable manipulation in unstructured household environments has driven rapid progress in embodied intelligence platforms. However, achieving a seamless transfer across the real-to-sim-to-real cycle faces three key challenges, including costly high-fidelity simulation scenes reconstruction, the complexity of systematic strategy evaluation in simulation, and incompatible real-world deployments. To address these challenges, we develop BestMan, a scalable and seamless real-to-sim-to-real platform that bridges the gap between the simulation and the real world, enabling effective strategy development, integration, and deployment for household mobile manipulation. Specifically, we design a novel Automated Scene Generation (ASG) module to reconstruct realistic...
论文介绍 家庭移动操作任务面临真实-仿真-真实转移的挑战，包括高保真仿真重建、策略评估和部署不兼容问题。本文开发BestMan平台，通过自动场景生成模块重建真实环境，支持策略仿真评估与集成，并简化现实部署。该平台为家庭机器人操作提供可扩展的无缝转移方案，促进策略开发与应用。
第一作者: Zecheng Yin · 方向: 导航与运动 · 来源: cs.RO
目标导航深度感知视觉语言高效导航探索策略
Abstract:To locate a target object while exploring the unknown environment is a fundamental capability for autonomous agents, with applications ranging from search-and-rescue to field robots. A simplified version of such task is Object Goal Navigation (ObjNav). In ObjNav, successful arrival at the target object provides a basic measure of performance; however, the efficiency of the navigation trajectory is equally important, as it indicates how intelligently the agent explores and how much time remains for subsequent tasks. In unknown environments, the key to efficient navigation lies in deciding where to explore next. While many prior works aim to address this core challenge and achieved promising performance in certain settings, recent training-based models and non-training frameworks still suffer from generalization and efficiency issues respectively, which in the worst cases can...
论文介绍 物体目标导航要求代理在未知环境中高效定位目标，但现有方法存在泛化和效率问题。本文提出EffiNav方法，融合深度和视觉-语言信息，优化探索决策以提升导航轨迹效率。该方法旨在解决智能探索问题，为自主代理如搜救机器人提供高效导航支持。
第一作者: Zhuowen Yin · 方向: 多模态具身 · 来源: cs.RO
具身基础模型安全对齐人类伤害预防数据集数据合成
Abstract:Embodied Foundation Models (EFMs) integrate multimodal understanding, future-state reasoning, and executable robot actions. Yet their safety alignment for human-injury prevention remains underexplored, primarily because real-world data of robots harming humans or creating hazardous household situations cannot be safely or ethically collected. To address this challenge, we propose a safety-critical data construction pipeline for human-injury prevention in this http URL from real DROID observations, our construction pipeline proceeds through scene understanding, hazard-aware image editing, temporal prompt generation, and single-pass rollout synthesis. The temporal prompts specify the expected scene evolution, while Wan2.7 synthesizes realistic robotic rollouts from the edited hazardous states in a single pass. Using this pipeline, we construct ROBOSHACKLES, a 10,000-clip robotic...
论文介绍 具身基础模型整合多模态理解，但安全对齐特别是人类伤害预防缺乏数据。本文提出安全关键数据构建管道，通过场景理解、危险图像编辑、时间提示生成和合成rollout，构建ROBOSHACKLES数据集。该数据集包含10,000个剪辑，用于训练防止人类受伤的模型，解决真实数据收集的伦理限制。
第一作者: Peibo Sun · 方向: 具身智能 · 来源: cs.RO
微创手术FBG传感器故障容忍Transformer自监督学习
Abstract:In minimally invasive surgical robotics, catheter-scale Fiber Bragg Grating (FBG) sensors are promising due to their ability to estimate multi-dimensional forces by multiplexing several optical channels. However, deploying these compact multi-channel sensors introduces two critical engineering challenges: inherent nonlinear cross-axis coupling during complex deformations, and intermittent channel dropouts caused by fiber fractures in constrained workspaces. These compounding issues severely degrade force estimation. Existing fault-tolerant approaches rely on combinatorial model banks, which scale exponentially with the channel count and demand prohibitively expensive per-pattern calibration. In this paper, we propose a unified, self-supervised mask-aware Transformer that explicitly models channel availability to enable graceful degradation under diverse and dynamic sensor...
论文介绍 微创手术机器人中，FBG传感器面临非线性耦合和通道丢失问题，影响力估计。本文提出自监督掩码感知Transformer方法，显式建模通道可用性，实现故障容忍力估计。该模型在自监督学习下处理动态传感器故障，提升力估计可靠性，为手术机器人传感提供新解决方案。
第一作者: Xiaowen Hu · 方向: 策略学习 · 来源: cs.RO
机器人跳跃SLIP模型强化学习敏捷运动混合控制
Abstract:Robotic jumping is pivotal in applications such as search and rescue and logistics, where crossing obstacles and enhancing mobility efficiency are critical. The Spring-Loaded Inverted Pendulum (SLIP) model leverages simplified spring-mass dynamics that naturally encode biologically plausible hopping motions, yet its performance degrades on irregular terrain due to idealized assumptions regarding contact and joint dynamics. Meanwhile, Reinforcement Learning (RL) can adapt to diverse and complex environments but often requires extensive data from unguided exploration. The complementary strengths of SLIP's physically grounded baseline and RL's adaptive capabilities motivate a hybrid framework that overcomes these individual limitations. We therefore propose Spring-loaded Reinforcement Learning (SRL), which integrates SLIP-based feedforward control signals with RL-driven real-time...
论文介绍 机器人跳跃在搜救和物流应用中能跨越障碍并提升移动效率。传统SLIP模型基于简化弹簧-质量动力学，在不规则地形上性能下降；强化学习虽能适应复杂环境，但需要大量数据。本文提出SRL混合框架，整合SLIP的物理基础控制和强化学习的实时自适应能力，以克服各自局限，提升机器人在复杂地形中的敏捷跳跃性能。
第一作者: Wei-Cheng Tseng · 方向: VLA 通用模型 · 来源: cs.RO
机器人基础模型策略评估视频生成自一致性多视角一致性
Abstract:Evaluating generalist robot manipulation policies in the real world is expensive, slow, and difficult to scale. Action-conditioned video world models offer a scalable alternative by simulating policy rollouts. Autoregressive rollouts accumulate compounding errors, observations across multiple camera views must remain mutually consistent, and the evaluator must generalize to policies whose behaviors lie outside the training distribution. We address these challenges with SC3-Eval, a self-consistent video generation recipe that adapts a pre-trained video foundation model into an accurate policy evaluator by enforcing three complementary forms of consistency. First, forward-inverse dynamics consistency jointly trains the model to predict frames from actions and to recover actions from frames, anchoring generated rollouts to a physically plausible action manifold and counteracting...
论文介绍 评估通用机器人操作策略在现实世界中成本高昂且难以扩展。SC3-Eval提出自一致性视频生成方法，利用预训练视频基础模型模拟策略执行，通过强制前向-逆向动力学一致性、多视角一致性和分布一致性，克服自回归累积误差和跨视角不一致问题，从而实现更准确、可扩展的策略评估。
第一作者: Antara Banerjee · 方向: 模仿学习 · 来源: cs.RO
机器人视觉检查导纳控制人机协作表面校准闭环控制
Abstract:Precision visual inspection underpins quality assurance across aerospace, semiconductor, and medical manufacturing, where undetected surface anomalies on high-value parts translate directly into scrap, rework, and field failures. Robotic visual inspection requires precise alignment between the end-effector and local surface geometry in the presence of perception noise and surface irregularities. In industrial settings, a human operator is often kept in the loop via teleoperation or shared autonomy, introducing real-time adjustments that render purely offline motion planning inadequate. This motivates control architectures capable of reactive, compliant behavior under combined human and perceptual uncertainty. This paper presents a novel real-time, closed-loop robotic orientation control pipeline for precision visual inspection, with an admittance-based framework that unifies...
论文介绍 精密视觉检查是航空航天等工业质量保证的关键。机器人视觉检查需在感知噪声和表面不规则性下实现末端执行器与表面的精确对齐，且人机协作引入实时调整。本文提出基于导纳的实时闭环控制框架，整合人类和感知不确定性下的合规行为，以实现更精确、自适应的视觉检查，提升工业检测效率。
第一作者: Seyed Alireza Azimi · 方向: 机器人操作 · 来源: cs.RO
强化学习机器人操作动作空间视觉基础模拟到现实迁移
Abstract:In real-world reinforcement learning (RL), the choice of action space can play a key role in shaping motion smoothness, safety, and overall task performance. In this study, we evaluate pose increment, pose velocity, joint position increment, and joint velocity across two vision-based manipulation tasks: object picking and pushing. We train policies in simulation and deploy them to the real world using sim-to-real transfer. We find that action-space representation indeed significantly affects sim-to-real performance. In particular, we find that the joint velocity action space is best for the vision-based picking and pushing tasks in terms of smoothness and final task performance. We also provide practical guidance for RL practitioners in choosing action spaces for both simulation and real-world experiments.
论文介绍 强化学习中动作空间的选择对机器人操作的运动平滑性、安全性和任务性能至关重要。本文在基于视觉的抓取和推物体任务中，评估位姿增量、位姿速度、关节位置增量和关节速度四种动作空间，通过模拟训练和现实部署。研究发现关节速度动作空间在平滑性和最终性能上表现最佳，为强化学习实践者提供了实用指导。
第一作者: Wenxi Chen · 方向: VLA 通用模型 · 来源: cs.RO
动作分块视觉-语言-动作模型潜在世界模型测试时扩展反应性执行
Abstract:Action chunking has become a common interface for vision-language-action (VLA) models, enabling low-frequency policy inference to drive high-frequency robot execution. However, once an action chunk is committed, its open-loop execution can be brittle under stochastic dynamics, hardware execution errors, and partial observability. We propose DREAM-Chunk, a test-time scaling method that augments chunking-based policies with a lightweight latent world model, without requiring additional policy fine-tuning. At test time, DREAM-Chunk samples multiple candidate action chunks, rolls out their predicted latent futures, and selects actions from the chunk whose predicted state best matches the observed rollout. In this way, DREAM-Chunk uses additional test-time computation to cover multiple plausible stochastic futures and improve reactivity during long-horizon chunk execution. On the...
论文介绍 动作分块是视觉-语言-动作模型的常见接口，但开放循环执行在随机动力学下易出错。DREAM-Chunk提出测试时扩展方法，集成轻量级潜在世界模型，无需策略微调。测试时采样多个候选动作块，模拟潜在未来状态，选择与观测最匹配的动作，从而提升长时域执行的反应性和鲁棒性。
第一作者: Marcos Abel Zuzuárregui · 方向: 具身智能 · 来源: cs.RO
任务规划大语言模型形式验证精准农业线性时序逻辑
Abstract:Though robotic systems are now being commercialized and deployed in various industries, many of these systems are highly specialized and often require an advanced skill set to operate and ensure they perform as instructed. To mitigate this problem, we recently introduced a mission planner leveraging LLMs to synthesize mission plans in precision agriculture based on mission descriptions provided in natural language. While the system demonstrates impressive performance, it also suffers from the inherent ambiguities of natural language. In this paper, we extend our system to address this issue by introducing multiple feedback loops in the planning architecture that leverage linear temporal logic (LTL) to ensure the mission planning system meets the specifications formulated by the user while still using natural language. To mitigate potential bias, this is achieved by using two...
论文介绍 机器人系统操作常需高级技能，现有任务规划器利用大语言模型基于自然语言描述合成计划，但存在语言模糊性。本文扩展该系统，引入基于线性时序逻辑的形式验证反馈循环，确保任务计划符合用户规格，同时保持自然语言接口，提升精准农业中任务规划的可靠性和易用性。
第一作者: Gershom Seneviratne · 方向: VLA 通用模型 · 来源: cs.RO
导航视觉-语言-动作模型第一人称视频几何轨迹监督场景重建流动匹配
Abstract:We introduce VEGA, an approach for training navigation VisionLanguage-Action (VLA) models from unlabeled egocentric navigation videos. Internet-scale egocentric videos provide a scalable source of navigation-relevant visual observations, capturing cluttered scenes, close-range obstacles, and natural human motion through real-world spaces. However, these videos are not directly usable for policy learning because they do not provide obstacle-aware trajectories conditioned on explicit navigation goals in the robot's coordinate frame. VEGA addresses this gap by reconstructing local scene geometry from monocular video, sampling navigation goals (represented as text, image, or spatial waypoints) and generating obstacle-aware trajectories using the constructed geometry. The resulting trajectory distribution is then used to train a flow-matching VLA navigation policy. By using...
论文介绍 训练导航视觉-语言-动作模型需要大规模数据，但互联网第一人称视频未提供障碍感知轨迹。VEGA提出从单目视频重建场景几何，采样文本、图像或空间目标，生成障碍感知轨迹，进而训练流动匹配VLA策略。该方法利用无标签视频提升导航策略在真实环境中的适应性和鲁棒性。
第一作者: Yuhang Huang · 方向: 机器人操作 · 来源: cs.RO
世界基础模型机器人操作3D一致性多视角扩散变换器
Abstract:World foundation models (WFMs) are powerful simulators, yet they predominantly operate in a single-view setting and lack the multi-view 3D consistency required for robotic manipulation. While robotic systems rely on multiple cameras (egocentric, eye-to-hand, and wrist-mounted) for policy learning, current multi-view world models simply concatenate view tokens without explicit geometric reasoning. This causes cross-view object drift, depth inconsistency, and texture misalignment. We trace these failures to two deficiencies: the absence of an explicit inter-view communication mechanism and the lack of a 3D geometric prior. We argue that resolving both simultaneously is necessary and sufficient. To address this, we present PAIWorld, a framework that augments diffusion-transformer world models via three core components: (1) Geometry-Aware Cross-View Attention blocks that establish...
论文介绍 世界基础模型在机器人操作中缺乏多视角3D一致性，导致跨视角物体漂移和深度不一致。PAIWorld提出增强扩散变换器框架，集成几何感知跨视图注意力块和3D几何先验，解决视图间通信和几何先验缺失问题，从而实现更准确的多视角世界建模，提升机器人操作策略学习。
第一作者: Haowen Liu · 方向: VLA 通用模型 · 来源: cs.RO
具身操控视觉语言模型工具使用代理框架
Abstract:Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents. Harnessing models through embodied tools use offers a promising alternative to end-to-end vision-language-action systems by combining high-level reasoning with external modules for perception, planning, and control. However, it remains unclear what makes an effective harness for embodied manipulation, and to what extent such a harness can unlock embodied capabilities in a wide range of reasoning models. In this work, we present Guava, a harness framework for embodied tool use developed through systematic exploration of the design space of agent workflows, action spaces, and observation spaces. Our study identifies three key ingredients for effective embodied agents: iterative perception-reasoning-action loops, semantic action abstractions, and multimodal...
论文介绍 该研究提出 Guava 框架，用于具身工具使用。通过系统探索代理工作流、动作空间和观察空间的设计，识别出有效具身代理的三个关键要素：迭代感知-推理-行动循环、语义动作抽象和多模态处理。这有助于结合高级推理与外部模块，提升具身操控能力，为通用具身智能提供实用方案。
第一作者: Bowen Li · 方向: 策略学习 · 来源: cs.RO
故障恢复技能学习概念发现抽象规划
Abstract:Intelligent robots should not only recover from failures, but also acquire the abstract knowledge needed to avoid them in the future. While reinforcement learning (RL) can learn reactive recovery behaviors, training a separate policy for every distinct failure mode is highly inefficient. We introduce Recovery-Driven Synthesis of Relational Concepts (ReSYNC), the first approach that progressively discovers and refines state abstractions (relational predicates) from failure-recovery experience to support abstract planning. Unlike purely reactive methods, ReSYNC jointly learns skills and concepts through an incremental dual-learning process. In the skill-learning phase, the robot uses RL to learn to recover from failures seen in training tasks. In the concept-learning phase, the robot discovers new relational predicates and refines its abstract planning model to explain and...
论文介绍 研究引入 ReSYNC 方法，使机器人不仅能从故障中恢复，还能通过增量双学习过程学习技能和关系概念。在技能学习阶段使用强化学习，概念学习阶段发现新谓词并精炼抽象规划模型，从而避免未来故障，提高从经验中学习的效率。
第一作者: Nikita Kachaev · 方向: VLA 通用模型 · 来源: cs.RO
视觉-语言-动作模型常识知识世界知识知识评估
Abstract:Embodied Vision-Language-Action (VLA) models are typically obtained by fine-tuning powerful pretrained VLMs on robotics data, yet it is unclear how much commonsense and factual knowledge they retain after adaptation. Failures on knowledge-sensitive tasks are ambiguous, conflating missing knowledge with poor generalization of low-level control. We introduce Act2Answer, a lightweight protocol that adapts VLM knowledge benchmarks to VLA evaluation by requiring agents to answer through action. Each question becomes a short tabletop episode where the agent performs a single object-placement action to select among candidate answers, yielding an action-grounded success rate with reduced control confounds. We curate a test suite of such environments across diverse commonsense and world-knowledge categories and introduce layerwise intent probing to localize answer-relevant information...
论文介绍 该研究提出 Act2Answer 轻量级协议，通过要求视觉-语言-动作模型以动作回答来评估其常识和世界知识保留。每个问题转化为桌面操作任务，减少控制混淆，并引入层级意图探针定位相关信息，以区分知识缺失和控制泛化问题。
第一作者: Zirui Zheng · 方向: 机器人操作 · 来源: cs.RO
记忆增强世界模型机器人操控多视图
Abstract:Action-conditioned world models have emerged as a promising paradigm for robot learning, offering a scalable alternative to costly real-world experimentation by generating action-consistent video rollouts. However, persistent world modeling remains challenging in manipulation: frequent end-effector occlusions and rapid wrist-camera motion make the current observation insufficient for predicting future views, causing models to forget or hallucinate scene details seen in earlier frames. Existing memory retrieval strategies often fail to identify informative history in dynamic manipulation scenarios. To address this limitation, we propose Mem-World, a memory-augmented multi-view action-conditioned world model. At its core, we present W-VMem, a 4D wrist-view-centered surfel-indexed memory that anchors historical observations to temporally evolving surface elements. By explicitly...
论文介绍 为解决机器人操控中的遮挡和运动导致的预测遗忘问题，提出 Mem-World 多视图动作条件世界模型。其核心是 W-VMem 记忆机制，基于表面元素索引历史观察，提高模型持久性和准确性，适用于动态操控场景。
第一作者: Runze Xu · 方向: VLA 通用模型 · 来源: cs.RO
潜在动作跨具身训练自我视频视觉语言模型
Abstract:Training generalist Vision-Language-Action(VLA) models typically requires massive, diverse robotic datasets with high-fidelity action annotations. While egocentric human manipulation videos are abundant and capture significant environmental diversity, the absence of action labels makes them difficult to use in conventional training paradigms. To address this, we propose a latent-action-based framework designed to extract general action priors from unlabeled human videos. The architecture features a Hybrid Disentangled VQ-VAE that decouples motion dynamics from environmental backgrounds through physical masks, enabling the construction of a cross-embodiment action codebook. By pre-training on human videos with the codebook, the VLM backbone learns deep representations of action intent. For adaptation to specific embodiments, we introduce an intent-perception decoupling strategy...
论文介绍 提出一个基于潜在动作的框架，从无标签人类自我视频中提取通用动作先验。使用混合解纠缠 VQ-VAE 解耦运动动态与环境，构建跨具身动作码本，用于视觉语言模型预训练，并通过意图感知解耦适应特定机器人具身。
第一作者: Jaeil Park · 方向: 机器人操作 · 来源: cs.RO
语义分割自监督学习户外场景DINOv3
Abstract:The GOOSE 2D Fine-Grained Semantic Segmentation Challenge at the ICRA 2026 Workshop on Field Robotics evaluates dense semantic segmentation of off-road imagery over a fine-grained taxonomy of 64 classes and 11 evaluated non-void coarse categories. We present the first-place solution to this challenge. Our solution comprises two complementary improvements: (a) a network-level design that combines a self-supervised DINOv3 ViT-L/16 backbone, a ViT-Adapter, and a Mask2Former mask-classification decoder, together with a coarse-category auxiliary loss on the global [CLS] token; and (b) an inference-time aggregation strategy based on multi-scale and horizontal-flip test-time augmentation and an ensemble of the top three checkpoints selected using Codabench scores. Our method achieves an official composite score of 76.57%, consisting of 69.32% fine-class mIoU and 83.81% category-level...
论文介绍 技术报告介绍在 ICRA 2026 GOOSE 2D 细粒度语义分割挑战中的获胜方案。采用自监督 DINOv3 骨干网络、ViT-Adapter 和 Mask2Former 解码器，结合推理时多尺度和翻转增强策略，在 64 类细粒度分割中取得高分。
第一作者: Yiyan Huang · 方向: 策略学习 · 来源: cs.LG
Wasserstein 距离离线策略学习分布结果因果推断
Abstract:Offline policy learning has received growing attention in causal inference. The primary objective is to learn a policy (individualized treatment rule) as a mapping from covariates to treatment that maximizes the empirical welfare defined as the mean of scalar-valued potential outcomes. In this paper, we study offline policy learning with distribution-valued outcomes, where each potential outcome is a probability measure on $\mathbb{R}$ and the reward is defined through a utility functional applied to the Wasserstein barycenter of induced outcome distributions. We establish statistical guarantees for the policy learning framework based on both Inverse Probability Weighting (IPW) and Doubly Robust (DR) estimators. By handling the challenging uniform deviation over the product of the combinatorial policy class and the infinite-dimensional quantile domain, we prove that the...
论文介绍 研究离线策略学习在分布值结果下的框架，其中奖励通过 Wasserstein 重心定义。基于逆概率加权和双重鲁棒估计器，建立统计保证，并处理组合策略类和无限维分位数域上的挑战，以支持因果推断应用。
第一作者: Juan Manuel Delfa Victoria · 方向: 机器人操作 · 来源: cs.LG
地球观测视觉语言模型在轨演示自主推理
Abstract:As Earth Observation data generation outpaces downlink bandwidth and human-in-the-loop processing, a widening gap has emerged between onboard collection and actionable ground intelligence. This paper presents NAVI-Orbital, a software system deployed on a Low Earth Orbit (LEO) spacecraft. On April 16, 2026, NAVI-Orbital achieved what is, to the authors' knowledge, the first in-orbit demonstration of a vision-language model performing autonomous multi-modal inference entirely onboard. NAVI-Orbital uses a local vision-language model (Gemma 3) to classify each captured scene, produce a text description of its content and the relationships between its features, and respond to operator follow-up via natural-language dialogue. The system is re-tasked through plain-English prompts in place of conventional command sequences, and is orchestrated by a graph-based state machine...
论文介绍 NAVI-Orbital 是首次在轨演示的视觉语言模型系统，部署在低地球轨道航天器上。它使用本地模型进行场景分类、文本描述和自然语言对话，通过英文提示重新任务化，实现自主多模态推理，提升地球观测数据的处理效率。
第一作者: Sneha Rao · 方向: 多模态具身 · 来源: cs.AI
视觉语言模型幻觉思维链检索增强生成可解释性
Abstract:Vision-Language Models (VLMs) remain prone to hallucinations, producing fluent but visually unfaithful outputs. Existing chain-of-thought and retrieval-augmented methods only partially address this, as they neither enforce step-level citation grounding nor route verification failures back to retrieval for correction. We present CaVe-VLM-CoT, a modular reflection-based agentic-RAG framework that enforces evidence-grounded reasoning through a five-stage closed-loop pipeline: Extractor, Retriever, Solver, Citation Injector, and Verifier, in which detected ungrounded claims trigger structured feedback to the Extractor for targeted re-retrieval. Since no existing framework jointly measures retrieval quality, step-wise citation faithfulness, and cross-modal grounding, we propose a suite of 23 component-wise metrics across all stages, anchored by CaVeScore, a composite metric...
论文介绍 本文针对视觉语言模型（VLM）易产生幻觉的问题，提出 CaVe-VLM-CoT 框架。该框架采用模块化反思代理-RAG 方法，通过五阶段闭环管道（Extractor, Retriever, Solver, Citation Injector, Verifier）确保推理有证据基础，并引入一套指标包括 CaVeScore 评估性能，以提高推理可解释性和准确性。
第一作者: Taewoon Kim · 方向: 具身智能 · 来源: cs.AI
人机协作城市搜索与救援情节记忆知识图谱图表示学习
Abstract:Effective human-robot teamwork requires robots to adapt to partners, situations, and task dynamics from the start of an interaction. In the MATRX Urban Search and Rescue (USAR) environment, people can externalize collaboration patterns (CPs) they discover during teamwork through a chat and reflection interface. We study whether a robot can use such prior team experience to become a better teammate in future interactions. To this end, we represent historical CPs as knowledge-graph episodic memories and use graph representation learning with a node-classification objective to identify a representative and effective memory for reuse. We then initialize the robot with this memory before a new collaboration episode begins. Across 20 participants and 160 round-level observations, initializing the robot with a single automatically selected prior CP increases rescue success from 25.7%...
论文介绍 本文研究在城市搜索与救援场景中提高人机团队合作，机器人利用情节记忆存储先验协作模式，通过知识图谱表示和节点分类学习来选择有效记忆重用，实验显示自动选择的记忆能提升救援成功率。
第一作者: Yizhuo Yang · 方向: 具身智能 · 来源: cs.AI
声源定位机器人听觉神经网络MUSIC算法混合框架
Abstract:Reliable sound source localization is fundamental to robot audition, enabling autonomous robots to perceive spatial cues and operate effectively in dynamic environments. Classical methods such as Multiple Signal Classification (MUSIC) offer strong theoretical foundations but degrade under low signal-to-noise ratios. While deep learning-based approaches achieve promising performance, they often struggle with limited generalization across conditions. To address these challenges, we propose NeuralMUSIC, a hybrid neural-subspace framework for robotic sound source localization. Specifically, a neural network first estimates the spatial covariance matrix from multichannel microphone observations. The predicted covariance is then integrated into a classical MUSIC pipeline with eigenvalue decomposition (EVD) and pseudo-spectrum computation, followed by a Frequency Attention Fusion...
论文介绍 本文提出 NeuralMUSIC，一种混合神经子空间框架用于机器人声源定位。通过神经网络估计空间协方差矩阵，集成到经典 MUSIC 管道中，并引入频率注意力融合，以提高低信噪比下的定位准确性和跨条件泛化能力。
美股技术面分化，标普500和纳斯达克ETF呈多头排列，接近52周高点，但微软、特斯拉等个股显示空头信号。加密市场普遍承压，比特币和以太坊处于空头趋势，加密恐慌贪婪指数为14的极度恐慌状态，总市值2.25万亿美元。中概股板块整体疲软，阿里巴巴RSI超卖至24.7，京东、拼多多等接近52周低点。商品外汇中，黄金期货出现MACD金叉但趋势中性，原油期货价格下跌，美元指数则接近52周高点并显示RSI超买。
标普500 ETF当前价格746.74，1日涨幅0.78%，5日涨幅1.22%，接近52周高点-1.8%。均线呈多头排列，SMA20为747.08，SMA50为729.66，SMA200为688.36，均低于或接近现价提供支撑。RSI14为54.1，处于正常区间，无超买超卖压力。MACD为3.93，低于信号线5.52，但整体技术趋势看涨，动量偏上。
阿里巴巴当前价格107.1，5日跌幅4.96%，远低于52周高点-44.41%。均线呈空头排列，SMA20为120.91，SMA50为129.3，SMA200为149.19，均高于现价形成阻力。RSI14为24.7，进入超卖状态，显示卖压较重。MACD为-6.30，低于信号线-4.84，强化下行趋势，技术面明显偏弱。
黄金期货当前价格4203，1日跌幅3.58%，但5日涨幅2.76%，走势震荡。价格低于SMA20（4375.63）、SMA50（4557.88）和SMA200（4436.31），面临上方压力。RSI14为37.8，处于正常区间，无极端信号。MACD出现金叉信号，但整体趋势为中性，反映市场观望情绪。
10Y美债收益率当前4.45%，1日跌幅0.8%，5日跌幅2.22%，但整体趋势看涨。均线呈多头排列，SMA50为4.42，SMA200为4.21，均低于现价，SMA20为4.52略高。RSI14为47，处于中性区间。MACD为0.015，低于信号线0.026，但技术面显示上行倾向，动量尚存。
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
本报告基于公开行情数据计算的技术指标，仅供技术指标解读参考。过去走势不代表未来表现，投资者应结合自身情况审慎决策。
The vice president delivered a rebuke to Israeli critics of the agreement, warning them not to alienate their most important ally, as the administration sought to rebut mounting criticism of the deal.
中文摘要 美国副总统万斯为特朗普政府与伊朗达成的协议进行辩护，并向以色列的批评者发出严厉警告，称不要疏远其最重要的盟友美国，以回应日益增长的批评声音。
The agreement accomplishes none of Israel’s stated war aims and arguably leaves the country in worse shape on each of them.
中文摘要 以色列对特朗普与伊朗达成的协议表示震惊，认为该协议未能实现以色列的任何既定战争目标，并可能使国家在各方面处境更糟。
Follow today’s news live • Get our breaking news email, free app or daily news podcast There were two small earthquakes in New South Wales this morning, according to Geoscience Australia. A 3.4 magnitude quake hit near Orange around 5.45am this morning, with at least 108 people reporting they felt t
中文摘要 澳大利亚参议院听证会上，针对KPMG泄露丑闻表达强烈不满，多项调查正在进行中。同时，新南威尔士州今晨发生里氏3.4级地震。
The attack, which shut down the capital’s airports for several hours, was part of an escalating campaign to bring the conflict home to Russians.
中文摘要 乌克兰对莫斯科炼油厂发动大规模无人机袭击，导致首都机场关闭数小时，这是冲突升级的一部分，旨在将战争带入俄罗斯本土。
Supporters call the bill a governance reform, while opponents see a turning point for Zimbabwe's political future.
中文摘要 津巴布韦一项旨在废除总统选举的法案引发激烈反弹，支持者称其为治理改革，反对者则视其为政治未来的重大转折点。
The campus opens to the public this weekend with a museum, community amenities and more to honour the 44th US president.
中文摘要 奥巴马夫妇主持芝加哥总统中心的盛大开幕，该中心设有博物馆和社区设施，于本周末向公众开放，以纪念美国第44任总统。
US vice president says 60-day negotiating period between Washington and Tehran has begun after deal to end war signed.
中文摘要 美国副总统万斯为伊朗协议辩护，美国宣布已解除对伊朗的海上封锁，华盛顿与德黑兰之间的60天谈判期正式启动。
In a sharp rebuke to critics of Trump’s deal with Iran, the vice-president referenced the billions in defence aid Israel recieves from the US News: Iran announces plans to bring in maritime fees for strait of Hormuz Analysis: Iran peace deal makes clear how far US has been forced to retreat since 20
中文摘要 副总统万斯尖锐批评以色列的伊朗协议反对者，称特朗普是他们仅剩的盟友，并提及以色列从美国获得的数十亿美元国防援助。
Ballots are being counted in the UK’s closely watched Makerfield by-election.
中文摘要 英国备受瞩目的Makerfield补选于近日开始计票，该选举受到密切关注，计票工作正在进行中。
The vice president said the United States had leverage to dictate the outcome of the next round of negotiations. But he claimed incorrectly that Iran got no new benefit from the lifting of oil sanctions.
中文摘要 副总统万斯为伊朗协议辩护，声称美国有主导下一轮谈判的杠杆，但错误地声称伊朗未从石油制裁解除中获得新利益。
Mosque leader says he was arrested and detained by immigration authorities for his Palestine advocacy.
中文摘要 美国法官下令释放被移民与海关执法局拘留的巴勒斯坦权利倡导者，该倡导者称因从事巴勒斯坦倡导活动而被捕。
Alexander Sokurov has questioned the Russian president about government repression, but he is still controversial among his country’s exiles.
中文摘要 俄罗斯导演亚历山大·索科洛夫曾质疑俄总统关于政府镇压的行为，但他在流亡者群体中仍存争议，被批评不够尖锐。
A man is being held on suspicion of attempted murder after a boy was critically injured when he ended up in a crocodile enclosure at a zoo outside Cambridge, the authorities said.
中文摘要 警方称，一名男子因涉嫌谋杀未遂被拘留，他在剑桥附近动物园迫使一名3岁男孩进入鳄鱼围栏，造成男孩严重受伤。
As US lifts its blockade, Tehran says fees to cover cost of managing waterway will come into effect at end of 60-day negotiation period Iran has announced plans to introduce a system of maritime fees in the strait of Hormuz in two months, after the 60-day period of negotiation that has been triggere
中文摘要 伊朗宣布计划在霍尔木兹海峡引入海运费，以支付水道管理成本，该费用将在美国解除封锁后的60天谈判期结束时生效。
Defense Secretary Pete Hegseth blasts NATO allies as a "paper tiger" while launching a six-month review of U.S. troop deployments in Europe and pressing for Europe to take the lead on its own defense.
中文摘要 美国国防部长皮特·赫格塞斯再次斥责北约盟友为「纸老虎」，并启动对驻欧美军部署的六个月审查，敦促欧洲主导自身防务。
South Korea’s producer prices rose in May at the fastest pace in nearly four years, as higher energy costs and a broad-based increase in industrial prices continued to filter through the economy.
中文摘要 韩国5月生产者价格指数以2022年以来最快速度攀升，主要受能源成本上升和工业价格上涨推动，显示通胀压力持续传导至经济。
Valar Atomics Inc., a Southern California-based startup, has reached a key milestone in its effort to develop small reactors under a US program aimed at accelerating the deployment of nuclear power.
中文摘要 美国核能试点计划下，南加州初创公司Valar Atomics Inc.在开发小型反应堆方面取得关键突破，旨在加速核能部署进程。
BHP Group shares fell after the company flagged a $2.3 billion writedown on its giant potash mine in Canada due to cost and time overruns for an expansion of the project.
中文摘要 BHP集团股价下跌，因其对加拿大大型钾矿项目的扩张出现成本和时间超支，公司宣布减记23亿美元。
South Korea is yet to resolve several key obstacles facing foreign investors, MSCI Inc. said in its latest market accessibility review, a setback for global funds and the government hoping the country’s reform drive could pave the way toward a future upgrade to developed-market status.
中文摘要 MSCI Inc.在市场审查中指出，韩国尚未解决外国投资者面临的关键市场障碍，这对政府改革推动升级为发达市场构成挫折。
Gold was on track for a third weekly loss, as a hawkish Federal Reserve and rate-hike bets outweighed the signing of an interim peace deal between the US and Iran.
中文摘要 黄金价格连续第三周录得周度下跌，因美联储的鹰派立场和加息预期超越了美伊临时和平协议签署带来的积极影响。
Telecom-infrastructure firm Extenet is facing a cash crunch that could force it to cease operations before the end of the month, according to a letter shared with the company’s bond investors.
中文摘要 电信基础设施公司Extenet警告，若未获得债券投资者救济，其现金将在数天内耗尽，可能于月底前停止运营。
The Japanese government’s new push to encourage companies to use their cash for longer-term growth is raising concerns it will lead to unprofitable investments and erode corporate value.
中文摘要 日本政府推动企业将现金用于长期增长，引发市场担忧这可能导致无益投资并侵蚀公司价值。
Attorneys general for California and Minnesota said the Commodity Futures Trading Commission isn’t equipped to handle gambling-associated issues like addiction, highlighting challenges the federal regulator faces as it aims to assert authority over prediction markets.
中文摘要 加利福尼亚州和明尼苏达州总检察长指出，商品期货交易委员会（CFTC）未准备好应对预测市场的赌博成瘾等社会成本问题。
Himalayan villages are creating artificial glaciers to guarantee water for their crops in the spring.
中文摘要 印度喜马拉雅山区的村庄正在建造人工冰川金字塔，以确保春季农作物的水源供应，应对气候变化影响。
Some insist on splitting the bill, others say the asker should pay, while many still see a man paying as romantic.
中文摘要 首次约会付账问题引发讨论：部分人主张分摊，有人认为邀请者应付，也有观点认为男方付款更浪漫。
With fuel and gas prices having fallen in recent days, we look at how the end of hostitlities might affect you - in five charts.
中文摘要 美伊临时和平协议签署后，燃料和天然气价格近期下跌，文章通过五个图表分析协议对个人财务的潜在影响。
Analysis showed how much the UK could have grown if it had not exited the EU.
中文摘要 英国央行公司数据显示，脱欧对英国经济造成的成本相当于其GDP的6%，分析指出若未脱欧经济增长可能更高。
9 回复 · 程序员 节点
6 回复 · Apple 节点
17 回复 · 程序员 节点
5 回复 · 程序员 节点
47 回复 · Apple 节点
24 回复 · Apple 节点
139 回复 · Apple 节点
24 回复 · Apple 节点
19 回复 · Apple 节点
11 回复 · Linux 节点
CHY公益站在此祝各位佬友端午安康，岁岁无忧，年年如意，万事顺遂，平安喜乐 CHY-API开发进度：已经完成后端，正在编写前端 22 个帖子 - 22 位参与者 阅读完整话题
感觉公益站本来很有意思很吸引人 自己开一个公益站果然就祛魅了，不过如此 开站！hlool公益站启动！（已允许注册，深夜福利） 开发调优 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 本站不保证使用，这波到什么时候封了就没了，目前测试200个号左右暂时不死，也可能随时就死 站点很小是小鸡，后面看看如果撑得久就再优化下，撑不住就就此告别 登录送100刀，看情况再继续优化 不会发渠道方案方式，希望可以活的久一点 仅gpt站点 上号太慢了太低估佬友们的速率了，加大下注册机封车，稍等优化完毕 稍微等下，L… 公益站Token滞销，救救我们 这回真睡了，希望可以帮到熬夜的佬们，严肃
于今日凌晨出现多位佬友发帖分享某公益站域名续费等帖子，且该情况持续 我们明白你们的喜悦之情，但是该行为已污染论坛信息流 此类话题已有对应的集中贴：https://linux.do/t/topic/1799316 如再出现对应情况我们将采取包括但不限于删除帖子，禁言等处理 感谢佬友们的理解 1 个帖子 - 1 位参与者 阅读完整话题
本帖使用社区开源推广，符合推广要求。我申明并遵循社区要求的以下内容： （点击了解更多详细信息） 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 1. 背景介绍 SubBoost 是一个 Clash/Mihomo 订阅转换、增强和管理工具。可以将机场订阅或自建节点转换为优化、统一的订阅，并自动更新。通过 UI 可视化，一键实现链式代理 、精确分流和防 DNS 泄露等高级功能。 经过半年的更新，目前 2.4.0 版本已经趋近于稳定，可以开放给大家自部署。再也不用担心因为 IP 限制而解析订阅失败啦。 当然，我部署的 在线版 依然会继续运行。 2. 部署教程 推荐部署在大陆服务器上，
我承认它很强。但是等 DeepSeek v4.1 一发布，这些套餐都白买。我说的，记住我的id。 46 个帖子 - 30 位参与者 阅读完整话题
一堆走4k接口的生1k图，生图站可以生4k图，就是记得选分辨率： 还是生4k价格图太高了吗？ 22 个帖子 - 21 位参与者 阅读完整话题
目前知道的办法收集 1.搞十几个谷歌号build轮询（一个号十几条但我感觉一天不太够，我roll都能几十次…） 2.GCP增金300美刀第一个月企业cli免费，同样要不停的换号（不喜欢折腾的可以不用看了） 3.相信公益站站长会带我们冲锋陷阵 4.反重力（好难吃甲很厚） 该怎么办啊啊啊哭死我了，想退坑了 156 个帖子 - 45 位参与者 阅读完整话题
经常看到朋友和同事在 Vibe Coding 时吐槽 ai 听不懂人话——“高级感”,“眼前一亮”,“再改改”，然后页面越来越乱。很多时候不是 AI 能力不行，更像我们是在用玄学抽卡。 LLM在pre-train和RL都用了海量的代码训练，自然英文术语的语义锚点会强于中文（而且中文语义信息熵太高了），打算长期整理一份术语速查表分享给佬友们，方便查阅 1. 字体分类与基本术语 (Font Classifications & Basics) Typography (文字排版) 文本的字体选择、间距调整、版面布局，以及最终在屏幕或纸张上的阅读呈现方式。好的排版会先给读者一个入口，再让他们知道哪里可以
[富可敌国] 0门槛拿【御三家 API】！GitHub Star＞1 就能领！最高送1000美金！ 核心福利（先到先得） 星火普惠：GitHub Star > 1 就能直接申请参与，0门槛直接白嫖生态基础资源！ 千星专享：Repo 只要过 1000 Star，官方直接砸 价值**$100 美金** 的API 额度！ 冲榜争霸：活动结束时最终冲到 Top 10 的神仙项目，还能再获得额外激励，其中Top 1 能独揽 价值**$1000 美金** 的API 额度！ 不搞虚的，只为同行：拒绝短期喧嚣，这次活动就是官方掏出真金白银致敬开源，帮开发者把 API 成本直接打到 0！ 活动时间：6月18日
财联社6月18日电，商务部等8部门关于加快“人工智能+消费"发展的实施意见，意见提出，加大财政等资金支持力度。 37 个帖子 - 32 位参与者 阅读完整话题