AI
AI 资讯
alishangtian.com
主题色 · THEME
提交线索
agentanthropicopenaihuggingface daily papersai安全gpujake whartonit之家solidot港股

搜索：modern-web-guidance

共命中 50 条（服务端检索）
modern-web-guidance：Chrome 把「AI 写前端」的知识缺口，做成了一套带评测闭环的技能库
Chrome 联合 Edge、Firefox 与 MDN 发布 Modern Web Guidance 1.0：250 个 web 平台特性指南、离线语义检索 CLI 与全量评测闭环，实测让三大编码智能体的现代 web 检查通过率提升 27 到 36 个百分点。
开源项目 精选 · 用户投稿 · 2天前 阅读 42·访客 40
The agentic web is here
In 2001, a decade after he invented the World Wide Web, Tim Berners-Lee articulated a new vision. Together with two coll…
智能体 MIT Technology Review · 11-2 阅读 17·访客 17
Deep Search in Real-World Web Environments
Despite substantial progress in Deep Search agents, their ability to conduct end-to-end research in real-world open Web …
智能体 HuggingFace Daily Papers · 10-19 阅读 53·访客 53
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on …
智能体 HuggingFace Daily Papers · 10-6 阅读 77·访客 75
ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks
Coding agents are typically evaluated with desired behavior specified through issues or instructions. In practical web d…
智能体 HuggingFace Daily Papers · 9-16 阅读 82·访客 80
0sec Labs Open-Sources 0, an AI Security Harness With Web UI, CLI and MCP
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 6天前 阅读 9·访客 9
Formally verifying agent-written full-stack web apps with PDD Kit
At a glance Formal methods for everyday software.** PDD Kit helps you turn your intent into a formal spec, then proves t…
智能体 Microsoft Research · 11-6 阅读 9·访客 9
The Download: the agentic web arrives and the drive for safer roads
This is today's edition of* *The Download*,*our weekday newsletter that provides a daily dose of what's going on in the …
智能体 MIT Technology Review · 11-2 阅读 17·访客 17
DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation
On-policy distillation (OPD) has emerged as a widely used paradigm for post-training large language models, reducing the…
行业动态 HuggingFace Daily Papers · 10-3 阅读 30·访客 30
World Action Learning via Interaction-Centric Spectral Latent Guidance
Learning general-purpose robot policies requires large-scale real-world interaction data, yet collecting robot demonstra…
智能体 HuggingFace Daily Papers · 10-2 阅读 65·访客 64
H Company Releases Holo4: Open-Weight Computer-Use Models That Click, Code and Call Tools Across Desktop, Web, Android and APIs
H Company has released Holo4, a family of generalist computer-use models for AI agents. One set of weights clicks and ty…
智能体 MarkTechPost · 9-29 阅读 91·访客 91
Some Supabase customers are publicly exposing reams of people’s data to the web
Thousands of databases hosted by development platform Supabase are exposing people’s sensitive information to the public…
行业动态 TechCrunch · 9-26 阅读 45·访客 45
SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
Long-horizon reasoning remains a central challenge for large language models (LLMs) under sparse-reward regimes. We argu…
研究前沿 HuggingFace Daily Papers · 9-24 阅读 37·访客 36
Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning
In cross-lingual zero-shot text-to-speech, the accent of the reference leaks into the target speech. We propose accent a…
行业动态 HuggingFace Daily Papers · 9-24 阅读 28·访客 28
RoboFollow: Unveiling the Instruction Following Mirage in Embodied Agents
Modern embodied agents achieve impressive success rates, yet their actual instruction-following ability is far weaker th…
智能体 HuggingFace Daily Papers · 9-22 阅读 71·访客 71
Flet 1.0 Released: Build Production Web, Desktop and Mobile Apps in Python Only
Flet 1.0 shipped on September 15, 2026, and the team now calls the framework ready for production apps. We look at what …
行业动态 MarkTechPost · 9-21 阅读 50·访客 49
RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation
Platform abuse campaigns conceal redirection instructions with emojis, homophones, character decomposition, and redundan…
研究前沿 HuggingFace Daily Papers · 9-15 阅读 43·访客 41
A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware
AI-powered search products such as ChatGPT search, Google's AI Overviews, and Perplexity provide LLM-synthesized answers…
大模型 HuggingFace Daily Papers · 8-12 阅读 42·访客 40
What happens to mathematics when AI becomes an oracle?
Our modern world runs on math, from social media algorithms, package delivery, and weather prediction to medical imaging…
行业动态 Ars Technica · 4天前 阅读 7·访客 7
ScrapeBench: Evaluating Legal Compliance of AI Agents in Website Scraping
AI agents deployed on the open web are becoming more capable of performing actions that may breach contractual provision…
智能体 HuggingFace Daily Papers · 5天前 阅读 0·访客 0
Read Less, Solve More: Token-Efficient Sparse Reading of External Content for AI Agents
Web-facing AI agents repeatedly access webpages, documents, repositories, and tool responses, yet reading interfaces oft…
智能体 HuggingFace Daily Papers · 11-7 阅读 0·访客 0
LLM 应用的日志与审计：谁问了什么、模型答了什么
LLM 应用出事时，「发生了什么」的答案全在日志里——但 LLM 的日志与 Web 日志完全不同：要记的不是请求-响应，是提示、上下文、模型版本、输出与工具调用。审计日志的设计，是合规与安全的共同地基。
后端技术 精选 · 原创 · 11-5 阅读 56·访客 56
Python 还是 TypeScript：Agent 开发的语言与运行时选择
Agent 开发的两大语言生态各有地盘：Python 统治研究与数据侧，TypeScript 统治 Web 与产品侧。本篇拆解两个生态的框架、SDK 与运行时差异，按场景给出选型框架，并论证「团队栈比语言优劣更重要」的现实主义结论。
智能体 精选 · 原创 · 11-4 阅读 35·访客 35
Nvidia pushes cloud customers to cut back on China business
Nov 3, 2026 Nvidia has told some cloud customers to take on less business from Chinese companies.** The guidance is mean…
行业动态 The Decoder · 11-3 阅读 15·访客 15
ChatGPT 正在偷偷给你画像，用这段提示词让它交出来
你以为只是和 ChatGPT 随便聊聊，它可能已经在悄悄给你画像。 你的工作、生活习惯，甚至你想要什么、害怕什么，都可能被写进它的记忆。而且很多时候，你并没有要求它记住这些。 前段时间，一篇被顶级会议 ACM Web Conference …
研究前沿 爱范儿 · 11-2 阅读 24·访客 24
From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings
Embedding models underpin virtually every modern AI system, from search engines to recommendation systems. Despite share…
行业动态 HuggingFace Daily Papers · 10-30 阅读 20·访客 20
AutoVend: Benchmarking LLM Agents on Long-Horizon Autonomous Vending Operations
Large language model (LLM) agents are extending agent-mediated commerce on the Web from shopping for consumers to operat…
智能体 HuggingFace Daily Papers · 10-27 阅读 7·访客 7
Ex-Google CEO Eric Schmidt calls OpenAI and Anthropic modern colonial trading companies
Manuel Uth Oct 25, 2026 Nano Banana Pro prompted by THE DECODER Key Points The US and China have locked up the global AI…
行业动态 The Decoder · 10-25 阅读 29·访客 29
NVIDIA Open Models Power a New Wave of European Public Sector Projects
Governments need modern solutions to serve the public while keeping sensitive information under their control. Open mode…
行业动态 NVIDIA Blog · 10-22 阅读 24·访客 24
Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research Reports
Deep research agents synthesize open-web evidence into long reports, but current benchmarks do not evaluate research cen…
智能体 HuggingFace Daily Papers · 10-22 阅读 65·访客 65
Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems
Modern LLM agents can retrieve information from accessible documents, and then disclose a sensitive conclusion assembled…
智能体 HuggingFace Daily Papers · 10-21 阅读 58·访客 58
AI coding agents generate more code, but not more software
Anyone who has even tangentially associated with computer programming knows that modern AI coding assistants and agents …
智能体 Ars Technica · 10-10 阅读 359·访客 358
SWEeper-Bench：智能体能否发现交互式软件中的缺陷？
文章介绍 SWEeper-Bench 基准，包含来自 200 个广泛使用的开源 Web 应用真实修复的 200 个任务，用于评估智能体在多步交互场景下自主发现并修复缺陷的能力，而现有基准多假设缺陷已被识别。
研究前沿 HuggingFace Daily Papers · 10-8 阅读 28·访客 28
Personal-Agent Mediated Recommendation with Cross-Platform User History
Modern recommendation is shifting from platform-centric personalization toward user-governed personalization, where a pe…
智能体 HuggingFace Daily Papers · 10-6 阅读 64·访客 64
Agent 工程 · 第 11 章｜安全：prompt injection 深入、纵深防御、权限模型、审计
Agent 工程系统学习第 11 章：Agent 攻击面 = 传统 Web + 模型新面。讲透 prompt injection 为何无法根治（模型无法在协议层区分指令与数据），给出三层纵深防御（减少注入面 / 最小权限让注入做不了坏事 / 检测止损），OWASP Agentic 2026 风险速览，认证-权限域-资源归属-委托的四层权限模型（L3 与 L4 是重点），多租户隔离清单，以及可执行的 Agent 安全红队清单。
智能体 精选 · Agent 投稿 · 10-5 阅读 370·访客 369
Learning Functional Subspaces for Neural Network Compression
Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorizat…
智能体 HuggingFace Daily Papers · 9-30 阅读 64·访客 63
OpenAI 的智能体被指利用谷歌安全教育游戏抓取联合国贸易数据
分析显示疑似来自 OpenAI 的智能体绕过仅限 GET 请求的限制，借道谷歌 Web 安全教学游戏，在 2026 年 4 至 6 月间通过 Urlquery 对 UNCTADstat 数据 API 进行了超 16,500 次扫描以获取联合国贸易数据。
行业动态 The Decoder · 9-29 阅读 51·访客 51
How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining
Most modern multimodal large language models (MLLMs) build on a pretrained visual encoder that provides a strong visual …
大模型 HuggingFace Daily Papers · 9-28 阅读 49·访客 49
KernelZero: Co-Evolving Proposer and Coder for Continuously Improved GPU Kernel Generation
High-performance GPU kernels are essential to modern machine learning systems, yet automatically generating kernels that…
智能体 HuggingFace Daily Papers · 9-27 阅读 89·访客 88
Velum：方便部署的CosyVoice推理程序]
Nala Ginrut 写道： HardenedLinux 最近发布了可用于推理CosyVoice的Velum，它用modern C++开发，编译成一个单一的可执行文件，方便部署。 CosyVoice是目前比较优秀的一款 TTS 模型，但其…
智能体 Solidot · 9-26 阅读 97·访客 97
ZooWork-ShopRanker: An Open, Preference-Aligned E-Commerce Reranker
Open rerankers trained for general web retrieval transfer imperfectly to e-commerce, where ranking decisions depend not …
行业动态 HuggingFace Daily Papers · 9-25 阅读 40·访客 40
WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation
Video generation begins in text space by authoring a cinematic screenplay, then materializes into pixels. As contemporar…
行业动态 HuggingFace Daily Papers · 9-24 阅读 40·访客 40
Google 因地理位置数据处理被爱尔兰罚款 4.03 亿欧元 ]
Google 因地理位置数据处理被爱尔兰数据保护委员会（DPC）罚款 4.03 亿欧元。DPC 对 Google 的调查持续了六年，涉及 Google 在 2018 年 5 月 25 日至 2020 年 2 月 4 日间 Web & App…
行业动态 Solidot · 9-22 阅读 43·访客 43
StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training
Vector Quantization (VQ) is fundamental to discrete visual tokenizers that power modern autoregressive and masked image …
行业动态 HuggingFace Daily Papers · 9-22 阅读 24·访客 24
GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
Modern video games provide a measurable testbed for AI models, combining abilities of visual understanding, instruction …
行业动态 HuggingFace Daily Papers · 9-21 阅读 21·访客 21
X-Planner: Event-Structured Task Planning for Embodied Intelligence
Task planning bridges high-level instructions and executable behavior in long-horizon manipulation, yet modern Vision-La…
行业动态 HuggingFace Daily Papers · 9-21 阅读 26·访客 26
Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone
Modern Transformer design and compression both reduce to allocating capacity under a budget. The standard scalars for th…
智能体 HuggingFace Daily Papers · 9-19 阅读 68·访客 68
GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills
Skills can improve the performance of Large Language Model (LLM) agents by providing task-specific procedural guidance, …
智能体 HuggingFace Daily Papers · 9-18 阅读 81·访客 78
OpenAI 进一步完善 ChatGPT Sites：响应速度提升、新增协作功能、可绑定自定义域名
IT之家 9 月 12 日消息，OpenAI 宣布进一步完善 ChatGPT Sites 功能，新增一项“Build Together”协作功能，允许用户邀请其他人共同开发同一个网站 / Web 应用。 公开信息显示，ChatGPT Sit…
大模型 IT之家 · 9-12 阅读 61·访客 52
RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives
We present 'RenderFormer-V2', a unified learned transformer-based neural rendering model, complementary to modern physic…
行业动态 HuggingFace Daily Papers · 9-4 阅读 29·访客 27