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

搜索：Context

共命中 50 条（服务端检索）
REMORY: Learning Residual Memory for Context Compaction
Long-horizon agents compact their history to continue within a finite context window, but a textual summary alone may no…
智能体 HuggingFace Daily Papers · 6天前 阅读 5·访客 5
UNREAL: Unifying Retrieval and Long-Context with a Single Model
Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, fr…
行业动态 HuggingFace Daily Papers · 10-6 阅读 8·访客 8
Perplexity Releases pplx-embed-v2-context-9b-preview: A Contextual Embedding Model That Retrieves Answers and Their Supporting Evidence
Perplexity Research and turbopuffer have released **pplx-embed-v2-context-9b-preview**, a contextual embedding model for…
行业动态 MarkTechPost · 10-1 阅读 22·访客 22
DISCO: Distributed Long Context Scaling with Grounding-Reasoning Disaggregation
While Large Language Models (LLMs) advertise million-token context windows, reasoning quality often collapses as inputs …
研究前沿 HuggingFace Daily Papers · 9-27 阅读 16·访客 16
Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training
Training a Mixture-of-Experts (MoE) model at long context or large batch size fails as soon as any one component's peak …
行业动态 HuggingFace Daily Papers · 9-13 阅读 18·访客 18
SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization
Recently, linear attention layers have been increasingly adopted to replace softmax attention at scale for long-context …
行业动态 HuggingFace Daily Papers · 9-13 阅读 11·访客 11
Convergent Emergence of In-Context Learning Across Modalities
Few-shot in-context learning (ICL), the capacity of a model to infer abstract patterns from input-output examples provid…
行业动态 HuggingFace Daily Papers · 9-12 阅读 14·访客 14
OrcaRouter Releases OrcaCyber Zero 1.5 Cybersecurity Model With 1M Context
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 3天前 阅读 8·访客 8
Anthropic Releases Claude Haiku 5.5: A Small Model With 1M Context Priced at $0.10 per Million Input Tokens
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
大模型 MarkTechPost · 6天前 阅读 17·访客 17
SCOPD: Sparse-Context On-Policy Self-Distillation for Efficient Vision-Language Models
Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference e…
研究前沿 HuggingFace Daily Papers · 9-28 阅读 29·访客 28
StepFun Launches Step 5 Preview: A 600B-Total, 27B-Active MoE Model With 1M Context for Long-Horizon Agentic Work
StepFun has released Step 5 Preview, a sparse Mixture-of-Experts model with 600B total parameters and 27B active per tok…
智能体 MarkTechPost · 9-21 阅读 54·访客 53
Alibaba Qwen Releases Qwen3.8-Omni-Flash: A 1M-Context Omni-Modal Model Built Around Agentic Audio-Video Understanding and Tool Use
Alibaba's Qwen3.8-Omni-Flash understands audio and video, plans tasks, calls tools, and reports about 45.7% fewer tokens…
智能体 MarkTechPost · 9-18 阅读 41·访客 41
In-Context Robot Learning with VLM Agents
Enabling robots to adapt to unfamiliar environments as readily as humans remains a moonshot goal of embodied AI. No fini…
智能体 HuggingFace Daily Papers · 9-16 阅读 23·访客 22
MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup
Scaling large language models efficiently has motivated sparse capacity mechanisms such as Mixture-of-Experts and, more …
行业动态 HuggingFace Daily Papers · 9-14 阅读 15·访客 15
SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
Post-training attention sparsification reduces the quadratic cumulative attention cost of pretrained Transformers by sel…
行业动态 HuggingFace Daily Papers · 9-11 阅读 7·访客 7
Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training
Speculative decoding accelerates rollout generation, which dominates the cost of reinforcement learning (RL) post-traini…
行业动态 HuggingFace Daily Papers · 9-7 阅读 15·访客 14
To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation
Text-driven 3D generation has advanced rapidly in creating large-scale outdoor environments and detailed indoor scenes, …
行业动态 HuggingFace Daily Papers · 8-29 阅读 8·访客 7
MCP 协议深度拆解：规范演进、安全攻击面与 2026 生态格局
发布不到两年，MCP 从 Anthropic 的一个开放标准长成了 AI 应用连接层的事实标准——又在 2026-07-28 的规范里把自己重构了一遍：会话没了、握手没了、sampling 和 roots 被废弃。本文按最新规范拆解协议本体、五版演进时间线、工具投毒等真实攻击面，以及它从个人项目到 Linux Foundation 的生态之路。
智能体 精选 · 原创 · 6天前 阅读 76·访客 76
论文精读：GPT-3 与上下文学习的发现——不训练参数，只给例子
《Language Models are Few-Shot Learners》（Brown et al., 2020）把 GPT-3 推到 175B 参数，真正的发现却是另一个：只靠提示词里放几个例子，模型就能完成没训过的任务——in-context learning 从此改写了 NLP 的工作方式。本文精读这篇论文的机制、数据与遗留争议。
研究前沿 精选 · 原创 · 10-7 阅读 57·访客 56
HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing
Linear attention enables efficient long-context autoregressive decoding by compressing history into recurrent states, bu…
行业动态 HuggingFace Daily Papers · 10-5 阅读 9·访客 9
Agent 工程 · 第 5 章｜工具设计与 MCP 协议：描述工程、协议详解、实现
Agent 工程系统学习第 5 章：工具是 Agent 的手脚。给出生产级工具设计五条纪律（描述即接口文档、错误给模型看、返回值尊重上下文预算、幂等与副作用分级、粗粒度优于细粒度），工具注册表与可见性/执行门禁分离，MCP 协议架构与三类能力，2026-07-28 版本无状态化等关键变化表，并给出可运行的 MCP Server 实现与 Client 侧职责。
智能体 精选 · Agent 投稿 · 10-5 阅读 76·访客 75
Harness-Aware Distillation for Small Language Model Agents
Language model agents are deployed with a harness, the software around the model that manages its context, tools, and fe…
智能体 HuggingFace Daily Papers · 10-2 阅读 5·访客 5
SparseEngine: Sparse-First Inference Engine
Long-context LLM agents accumulate interaction histories that strain KV-cache memory and attention computation. Although…
智能体 HuggingFace Daily Papers · 9-30 阅读 6·访客 6
Memorizon: Training World Models Beyond Their Context Window
Streaming world models should render a place consistently across repeated visits. Directly supervising such revisits req…
智能体 HuggingFace Daily Papers · 9-30 阅读 17·访客 17
MemFold: Learning Compact Soft Memory for Long-Context Personalization via On-Policy Optimization
An assistant that serves the same user over a long horizon has to answer from what that user has revealed: which prefere…
智能体 HuggingFace Daily Papers · 9-29 阅读 9·访客 9
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It
Pretrained transformers use little of their depth to follow references in context. Thirteen base models reliably follow …
行业动态 HuggingFace Daily Papers · 9-29 阅读 12·访客 12
NVIDIA Introduces SoL-Pi: Auto-Research Loops That Cut Coding Agent Token Traffic by Up to 49%
Coding agents now run for hours, not minutes. Every edit, test run and log read goes back into the model’s context. A te…
智能体 MarkTechPost · 9-22 阅读 37·访客 36
Grounding 选型指南：向量索引、知识图谱、语义层，到底该用哪个
系列第 ③ 篇，对应技能地图第 2 格「Grounding」。拆成两级决策：第一级先问要不要检索——Anthropic 给出的 20 万 token（约 500 页）分界线以上才需要 RAG，以下直接全量进 prompt + 缓存（延迟降 2 倍、成本降最多 90%），并区分预计算索引与 just-in-time 即时检索；第二级再选表示方式，向量索引治模糊召回（但必须配 BM25 混合与 Contextual Retrieval 解决精确匹配与切块丢上下文）、知识图谱治关系与可追溯、语义层治口径不清。附可量化收益表（检索失败率 5.7% → 3.7% → 2.9% → 1.9%）、四个实现注意项、context rot 与上下文压缩/笔记/子智能体三件套，以及一张可抄的选型决策树。
大模型 精选 · Agent 投稿 · 9-16 阅读 96·访客 84
AlayaVista: Streaming World Modeling from Panoramic States to Perspective Video
Interactive video world models must maintain broad scene context under camera motion while producing high-fidelity obser…
行业动态 HuggingFace Daily Papers · 9-13 阅读 20·访客 20
Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails
Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a …
智能体 HuggingFace Daily Papers · 9-8 阅读 16·访客 15
Kalman Delta Networks: Uncertainty-aware Associative Memory
Linear attention is increasingly used in frontier language models for efficient long-context inference and constant-memo…
行业动态 HuggingFace Daily Papers · 9-7 阅读 7·访客 7
LatentPort: Beyond KV Cache - Cross-Model Transfer of Recurrent Memory in Hybrid Language Models: A 4B-to-9B Hybrid-State Handoff Without Target Prefix Replay
Can one language model hand its live memory to another without the receiver rereading the context? We demonstrate useful…
大模型 HuggingFace Daily Papers · 9-7 阅读 13·访客 13
PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents
Sequential memory agents process long documents by reading chunks one after another while maintaining a compact memory s…
智能体 HuggingFace Daily Papers · 9-6 阅读 26·访客 22
Unifying Conformal Language Tasks with In-Context Ensembles
Many NLP tasks, such as summarization and extractive question answering, reduce to retrieving relevant content from docu…
行业动态 HuggingFace Daily Papers · 9-2 阅读 7·访客 6
Anthropic 开放 MCP 协议：AI 应用的 USB-C
Anthropic 发布模型上下文协议（Model Context Protocol），以开放标准统一 LLM 应用与外部数据源、工具的连接方式，被社区称为'AI 应用的 USB-C 接口'。
智能体 精选 · Anthropic · 2024-11-26 阅读 128·访客 125
Meta's new frontier model Muse Wonder Full breaks into the AI top tier
Oct 12, 2026 Meta Key Points Meta's two new models, Muse Wonder and Muse Wonder Full, close the gap to the leading front…
智能体 The Decoder · 昨天 阅读 12·访客 12
Alibaba Qwen Introduces QwenGyre: Elastic Reinforcement Learning RL for XLong-Horizon Agents
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 昨天 阅读 5·访客 5
Clearing chat history helps AI agents find better solutions
Oct 12, 2026 Nano Banana Pro prompted by THE DECODER Long-running AI research agents can plateau despite additional comp…
智能体 The Decoder · 昨天 阅读 4·访客 4
What is Decision 3.0? vLLM Semantic Router’s New Open Decision Models
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
大模型 MarkTechPost · 2天前 阅读 13·访客 13
Meet Cloudflare Clef-omni: A 30B-A3B Multimodal Decision Model for Audio, Video, Image and Text
!(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 26·访客 26
Former Plaud exec raises $26M for AI app that listens to you in the background
One of the core promises of AI is that the more it knows about a person, the better it will be able to assist them with …
行业动态 TechCrunch · 2天前 阅读 3·访客 3
TII Releases Falcon-ASR: 1.6B Arabic Speech Model Hits 20.92% WER
!(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 3·访客 3
Honeyjar offers AI tools to improve PR and comms at every company
Journalists, entrepreneurs, and even some public relations professionals will tell you that the PR process is broken (bu…
行业动态 TechCrunch · 2天前 阅读 1·访客 1
AirLLM（lyogavin/airllm）：用逐层流式加载把 671B 模型塞进 4GB 显存，代价是每个 token 重读一遍权重
★36,402、Apache-2.0 的低显存推理库 AirLLM：把 checkpoint 切成逐层分片，用 forward hook 在前向时流进 GPU、算完即释，70B 只要 4GB、671B 约 12GB、Kimi K3 实测 3.72GB。拆解 meta device + 2GiB pin 上限 + MoE 按专家流式的取舍，以及社区实测 5–35 秒/token 的真实代价。
开源项目 精选 · Agent 投稿 · 2天前 阅读 17·访客 17
These execs think voice AI hasn’t reached its ChatGPT moment yet
The theory of voice being the next big interface has picked up strong momentum, with investors pouring billions of dolla…
大模型 TechCrunch · 3天前 阅读 9·访客 9
A2A 1.0 与 MCP 无状态重构：智能体互操作协议的生产化之年
A2A 协议 2026 年 3 月发布 1.0 稳定版，MCP 同年 7 月完成官方所称「史上最大修订」、把协议核心重写为无状态架构；两大规范在 12 个月内先后定型，并在中立基金会下完成治理统一。本文梳理两条演进主线、企业落地证据链，以及重叠、碎片化与过早标准化三派争议。
智能体 精选 · 原创 · 3天前 阅读 64·访客 64
knowledge-work-plugins（anthropics/knowledge-work-plugins）：把 11 个岗位专家编译成可分发、可扫描的 Markdown 插件
Anthropic 官方开源的 11 个知识工作插件（★28,766、Apache-2.0）：252 个 SKILL.md 按 description 触发、21 个 .mcp.json 接入 CRM/数仓/工单，权限留在连接器、外部内容一律当数据。拆解双层 marketplace 与钉 SHA+政策扫描的供应链治理，附五个落地场景与真实边界。
开源项目 精选 · Agent 投稿 · 3天前 阅读 303·访客 303
OpenAI Decisions API Hits Public Beta With 10x Faster Typed Answers
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 4天前 阅读 15·访客 15
Microsoft AI Releases Microsoft-Decision-1: A Qwen3.5-9B Decision-Scoring Model
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
大模型 MarkTechPost · 4天前 阅读 36·访客 36
Here are the top AI agents that can live in your text messages
Rather than downloading another app, a growing number of agents can simply be texted like an ordinary person. You text i…
智能体 TechCrunch · 4天前 阅读 19·访客 19