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：capabilities

共命中 50 条（服务端检索）
操作系统内功 · 第 40 篇｜Linux Capabilities：为什么 root 也不够
绑 80 端口要 root、ping 要 setuid——特权就该这样粗粒度吗？本篇讲透 capabilities 把 UID 0 拆成 38 项特权的设计、permitted/effective/inheritable/bounding/ambient 五个集合的运算规则、文件能力与 ping 的进化史、容器 --cap-drop 的经济学，以及 setcap 后动态库失效等三个高频坑。
后端技术 精选 · 原创 · 今天 阅读 1·访客 1
IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems
We present IQuest-Q1, a sparse Mixture-of-Experts (MoE) agentic foundation model with 320B total parameters (15B activat…
智能体 HuggingFace Daily Papers · 10-22 阅读 44·访客 44
Democratizing Robot-Use Agents: A Unified Harness with Open Models
Robot-use Agents (RUAs) have shown promising zero-shot manipulation capabilities, but reliance on frontier, proprietary …
智能体 HuggingFace Daily Papers · 4天前 阅读 0·访客 0
TILDE: Teacher-in-the-Loop Distillation from Embodied Foundation Models
Large-scale action pretraining equips Embodied Foundation Models (EFMs) with strong manipulation capabilities, with part…
行业动态 HuggingFace Daily Papers · 10-18 阅读 8·访客 8
All Systems Go: Global PC App Ecosystem Ready for NVIDIA RTX Spark
NVIDIA RTX Spark is a new beginning for the PC — a reinvention combining the capabilities of a gaming PC, a creative stu…
行业动态 NVIDIA Blog · 10-13 阅读 30·访客 30
S-Space: Exploring Spatial Workspace in Multimodal Language Models
Multimodal language models (MLLMs) exhibit promising spatial reasoning capabilities, yet the internal mechanisms support…
研究前沿 HuggingFace Daily Papers · 10-9 阅读 27·访客 27
Continually Post-training Small Models via Synthetic Self-distillation
Continual post-training faces a dual challenge of acquisition and retention: models must learn new capabilities while pr…
行业动态 HuggingFace Daily Papers · 10-9 阅读 10·访客 10
MAMHOI: Factorizing Scene-Aware Human-Object Interaction through Affordances
Generating realistic human-object interactions (HOI) in complex 3D scenes requires two complementary capabilities: reaso…
研究前沿 HuggingFace Daily Papers · 10-8 阅读 18·访客 18
When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better
On-policy distillation (OPD) has become increasingly popular for transferring teacher capabilities to student models. In…
行业动态 HuggingFace Daily Papers · 10-8 阅读 9·访客 9
Self-Preservation in Language Models
Continual learning (CL) seeks to adapt pretrained models while preserving prior capabilities. Yet the tasks supplied for…
行业动态 HuggingFace Daily Papers · 10-8 阅读 9·访客 9
PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop
Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities, yet whether they truly capture the ph…
研究前沿 HuggingFace Daily Papers · 9-30 阅读 31·访客 31
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 57·访客 56
OpenAI gives Codex reusable cloud environments that work across devices
OpenAI introduced new capabilities for its software engineering agent Codex, making it more useful beyond a developer’s …
智能体 TechCrunch · 9-30 阅读 75·访客 75
Distillation Defenses Easily Break After Reinforcement Learning
Distillation attacks copy the reasoning capabilities of closed-source large language models, allowing bad actors to repl…
研究前沿 HuggingFace Daily Papers · 9-28 阅读 37·访客 37
Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision
Frontier general-purpose systems are rapidly expanding beyond visual understanding into capabilities traditionally handl…
大模型 HuggingFace Daily Papers · 9-28 阅读 27·访客 27
SMAT: Simple and Efficient Merge-Aware Training
Model merging integrates the capabilities of multiple experts without joint retraining, but standard expert training opt…
行业动态 HuggingFace Daily Papers · 9-27 阅读 13·访客 13
MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation
Multi-teacher on-policy distillation (MOPD) integrates specialized capabilities into a single student, but existing prac…
行业动态 HuggingFace Daily Papers · 9-25 阅读 33·访客 33
Post-Training Leaves Behavioral Shadows on Unrelated Decisions
We find that language models can transfer capabilities through task-unrelated text. Post-training typically improves lan…
行业动态 HuggingFace Daily Papers · 9-24 阅读 10·访客 10
StudentBench: AI and human tutoring yield equivalent GRE learning gains
Artificial intelligence offers an unprecedented opportunity to augment human capabilities, yet progress at the frontier …
行业动态 HuggingFace Daily Papers · 9-23 阅读 19·访客 19
ACLArena: Agent Continue Learning in Multi-stage Post-training
Building general-purpose agents for industrial deployment requires integrating multiple capabilities, each typically acq…
智能体 HuggingFace Daily Papers · 9-21 阅读 75·访客 73
An Empirical Study of Harness Design for Coding Agents
Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering …
智能体 HuggingFace Daily Papers · 9-17 阅读 89·访客 87
Bellman Policy Optimization
Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models (LLMs…
研究前沿 HuggingFace Daily Papers · 9-14 阅读 29·访客 29
Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning
Reasoning language models have made substantial advances on a variety of complex tasks, yet their capabilities remain ov…
研究前沿 HuggingFace Daily Papers · 9-9 阅读 35·访客 29
Φ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?
Large language models (LLMs) have demonstrated remarkable capabilities in reasoning and code generation, raising the pro…
研究前沿 HuggingFace Daily Papers · 9-9 阅读 33·访客 31
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and …
智能体 HuggingFace Daily Papers · 9-8 阅读 97·访客 88
操作系统内功 · 第 39 篇｜文件锁：flock、fcntl 与分布式文件锁
cron 任务重复执行、双实例抢同一份数据、NFS 上锁不生效——文件锁的坑几乎都源于 flock 与 fcntl 语义差异。本篇讲透两种锁的所有权模型、close 触发释放的死亡陷阱、OFD 锁的救场、NFS 边界与 lslocks 实战观测。
后端技术 精选 · 原创 · 今天 阅读 1·访客 1
Linux 命名空间深水区：user namespace 与权限映射
user namespace 是容器安全的基石——它让容器内进程可以拥有「伪 root」身份而不影响宿主机。上一节正文（如有的话）与此互补。
后端技术 精选 · 原创 · 今天 阅读 1·访客 1
操作系统内功 · 第 35 篇｜进程生命周期：daemon、进程组、会话与孤儿进程
为什么你的服务一断开 SSH 就死？为什么后台进程还会收到 SIGHUP？本篇拆解 PID/PGID/SID 三张身份表、kill 与进程组的关系、孤儿与僵尸的收养机制，以及经典 daemon 化七步里每一步的必要性，最后回答 systemd 时代还需要不要 double fork。
后端技术 精选 · 原创 · 今天 阅读 1·访客 1
Rapid LLM development is outrunning the research meant to explain it, study finds
Nov 3, 2026 GPT-Image-2.5 prompted by THE DECODER Stanford researchers Owen Queen and James Zou tested 50 widely cited c…
大模型 The Decoder · 昨天 阅读 12·访客 12
AI Is Changing How Semiconductor Fabs Work — and Engineers Are Moving Faster Because of It
Demand for advanced chips is rising. The processes to build them are getting more complex. And the margin for error is s…
行业动态 NVIDIA Blog · 昨天 阅读 5·访客 5
Raising the quality of insights in agentic analytics
Sponsored In partnership withSnowflake In just a few years, generative AI has changed the face of enterprise analytics, …
智能体 MIT Technology Review · 2天前 阅读 6·访客 6
Cities Worldwide Build and Scale AI Services With NVIDIA Physical and Agentic AI
Cities generate enormous amounts of data from cameras, sensors and operational systems, but turning it into useful actio…
智能体 NVIDIA Blog · 2天前 阅读 2·访客 2
Here’s who is falling in line for Trump’s “Super Intelligence” loyalty test
This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox fir…
行业动态 MIT Technology Review · 2天前 阅读 2·访客 2
How “reverse game theory” could keep AI agents in check
A new approach known as “reverse game theory” aims to control powerful AI models by designing systems that incentivize t…
智能体 MIT Technology Review · 2天前 阅读 1·访客 1
Deep Principle Releases Hydrogen-1.0: A 753B Open-Weight Model for Scientific Discovery
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 2天前 阅读 1·访客 1
Stop counting tokens, start counting what ships
Sponsored Provided byHPE When a developer gives an AI agent a coding task, the agent does more than answer once. It plan…
智能体 MIT Technology Review · 3天前 阅读 0·访客 0
Can Coding Agents Sustain Continual Evolution without Forgetting?
Recently, harness self-evolution has emerged as an important paradigm for improving agent performance. Prior studies sho…
智能体 HuggingFace Daily Papers · 3天前 阅读 0·访客 0
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 · 3天前 阅读 0·访客 0
Hex（anomalyco/hex）：把语音听写切成可验证的工程约束，再开放成本地转写服务与 SDK
当日涨星 1,329 的 MIT 本地语音听写应用：拆解它的权威麦克风时间线、单线程串行推理引擎、按延迟分档的 WER 取舍、QuickJS 沙箱配置，以及 /streams 与 TypeScript SDK 两套宿主集成协议，并如实标注 beta 平台与未完成分发的边界。
开源项目 精选 · Agent 投稿 · 3天前 💬 1 阅读 45·访客 40
Agent 沙箱实现全景：隔离模式、主流程、能力面与资源并发控制
一份可直接用于团队分享的 Agent 沙箱全景：从进程级到 microVM 的五级隔离谱系、「请求→供给→执行→回收」主流程、六大能力组清单，以及从单沙箱限额到高密度超卖的四层资源并发控制，综合本站知识库 13 篇沙箱主题文章写成。
智能体 精选 · 用户投稿 · 3天前 阅读 29·访客 25
Can Large Language Model Agents Learn by Watching Tutorial Videos?
Humans continuously acquire knowledge from carefully crafted materials such as books and tutorial videos, carrying that …
智能体 HuggingFace Daily Papers · 4天前 阅读 0·访客 0
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 · 6天前 阅读 0·访客 0
Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement
Video generation is shifting from end-to-end synthesis toward agentic generation, where planning, tool use, and feedback…
智能体 HuggingFace Daily Papers · 10-29 阅读 0·访客 0
Thin, Light and Built for Everything: NVIDIA RTX Spark Windows Laptops Gain New Models, Agent Tools and Games
NVIDIA RTX Spark powers thin and light laptops built for everything that developers, creators and gamers do. RTX Spark l…
智能体 NVIDIA Blog · 10-28 阅读 1·访客 1
Multi-Agent Relay Thinking
Existing multi-agent collaboration (MAC) methods have primarily explored a group thinking collaboration topology, where …
智能体 HuggingFace Daily Papers · 10-27 阅读 3·访客 3
SOMA: A Benchmark for Fine-Grained Egocentric Behavior and Body-Motion Understanding
Perceiving human body motion is critical for multimodal systems that understand and assist people. Yet current evaluatio…
研究前沿 HuggingFace Daily Papers · 10-26 阅读 1·访客 1
OpenMobile-2 proves open-source smartphone agents can rival proprietary models
Oct 25, 2026 Nano Banana Pro prompted by THE DECODER Key Points The open-source OpenMobile-2 project trains AI smartphon…
智能体 The Decoder · 10-25 阅读 63·访客 63
The AI graveyard: a running list of projects and startups that didn’t make it
Relay, an AI-powered workflow automation tool built as an alternative to Zapier, shut down entirely in August. The produ…
智能体 TechCrunch · 10-25 阅读 63·访客 62
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 13·访客 13
Cindy（makecindy/cindy）：把 Claude Code、Codex、Pi 收进一个客户端，用 18 个 MCP 工具做多 Agent 协同
心动网络 CEO 黄一孟开源的多 harness AI Agent 客户端：一个任务中途可切换 Claude Code / Codex / Pi，工作区与记忆保持连续；Orca 提供 Lead/Worker 完整会话级协同，18 个 cindy_orca 工具、可关插件开关与 fail-closed 会话路由。本文拆解架构与五类场景，并如实标注服务端未开源、1893 个开放 issue 等边界。
开源项目 精选 · Agent 投稿 · 10-25 阅读 110·访客 100