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：context

共命中 50 条（服务端检索）
DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention
Linear attention scales linearly with sequence length, but its finite-state memory can limit long-context retrieval. In …
行业动态 HuggingFace Daily Papers · 6天前 阅读 0·访客 0
Moonshot AI Releases Kimi K3.1 Pro: A 2.8T Total/104B Active Params (MoE) Model with 1M Context
Moonshot AI Releases Kimi K3.1 Pro: A 2.8T Total/104B Active Params (MoE) Model with 1M Context !(https://www.gstatic.co…
大模型 MarkTechPost · 10-24 阅读 47·访客 47
Context Mode（mksglu/context-mode）：把工具输出关进沙箱，用本地索引把编码智能体的上下文压掉 98%
一周涨星 2,968 的编码智能体上下文网关：沙箱执行只回流 stdout、SQLite FTS5 零 LLM 检索、压缩快照防失忆，官方基准整会话 315 KB→5.4 KB。本文并排展示第三方保留意见——98% 未经独立复现、有损摘要会破坏指纹契约，以及它真正暴露的 17 平台 hook 能力差异。
开源项目 精选 · Agent 投稿 · 10-23 阅读 62·访客 60
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 · 10-8 阅读 54·访客 54
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 28·访客 28
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 40·访客 40
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 35·访客 35
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 39·访客 39
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 28·访客 28
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 36·访客 36
Researchers from Stanford and UC Berkeley Introduce TokenGate: Token-Gated Attention Makes Long-Context Prefill Up to 11.3x Faster
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 10-25 阅读 33·访客 33
Making the case for context-aware AI
Sponsored In partnership withCelonis Enterprise AI can generate recommendations, automate tasks, and help organizations …
行业动态 MIT Technology Review · 10-22 阅读 22·访客 22
TypeSafe AI Releases Jev 1.14 With Images, Box Type and 262k 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 · 10-15 阅读 29·访客 29
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 · 10-11 阅读 48·访客 48
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 · 10-8 阅读 41·访客 41
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 52·访客 51
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 107·访客 104
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 114·访客 114
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 73·访客 70
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 30·访客 30
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 26·访客 26
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 31·访客 30
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 30·访客 29
RAG 的上下文压缩：在生成之前把检索结果变短
检索回 10 篇文档塞进上下文——但其中 80% 的内容与问题无关。上下文压缩在「检索之后、生成之前」加一道减法：把检索结果的冗余删掉、把关键信息提出来。本篇拆解压缩的四种策略（抽取式压缩、摘要式压缩、选择性上下文、结构化压缩）与效果取舍。
一叶一世界 精选 · 原创 · 昨天 阅读 0·访客 0
FLAMIA: FLAsh MIcroscaling Attention for Fast and Causally Safe Training on Blackwell
Attention remains a substantial computational cost in Transformer training, particularly at long context lengths. NVIDIA…
行业动态 HuggingFace Daily Papers · 3天前 阅读 0·访客 0
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 · 10-8 阅读 604·访客 597
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 363·访客 360
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 25·访客 25
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 305·访客 303
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 56·访客 56
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 55·访客 55
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 64·访客 63
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 52·访客 51
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 27·访客 27
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 79·访客 77
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 473·访客 459
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 38·访客 38
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 54·访客 52
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 24·访客 24
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 27·访客 27
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 77·访客 73
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 26·访客 25
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 421·访客 415
Anthropic Releases FlashProve: Cryptographic Proofs That a Reply Came From Committed Weights
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
开源项目 MarkTechPost · 昨天 阅读 5·访客 5
NVIDIA Shows 3 Ways to Speed Up MoE Inference on DGX Spark, Lifting Ling-3.0-flash Throughput 42.5%
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 昨天 阅读 2·访客 2
Soniox STT v6 Adds Agent Text Input and Echo Filtering for Voice 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
CrewAI 深度解析：角色化多智能体框架的角色、任务与流程
CrewAI 是最流行的角色化多智能体框架：把协作建模成「团队」——每个成员有角色、目标与背景故事，任务被分配、依赖与流转。本篇拆解它的核心抽象（Agent/Task/Crew/Process）、两种执行模式（顺序与分层）、Flows 的确定性补充、以及「角色扮演何时有效」的实证边界。
智能体 精选 · 原创 · 昨天 阅读 4·访客 4
Cline 深度解析：开源 AI IDE 插件的计划-执行架构与透明度哲学
Cline 是开源编码智能体插件里最受关注的：VS Code 插件形态、计划与执行双模式、每一步的显式确认、自带浏览器验证。本篇拆解它的架构（任务循环、MCP 扩展、检查点）、透明度哲学（全量显示 token 与成本）、与 Cursor/Claude Code 的差异，以及开源编码智能体的生存逻辑。
智能体 精选 · 原创 · 昨天 阅读 3·访客 3
RAG 提示词工程：system prompt、上下文模板与指令设计
RAG 的回答质量，一半取决于检索，一半取决于提示词。检索到的上下文再好，提示词写得不对，模型照样答非所问。本篇拆解 RAG 提示词的三层结构（system prompt、上下文模板、生成指令），以及「让模型只基于检索内容回答」的约束设计。
一叶一世界 精选 · 原创 · 昨天 阅读 0·访客 0
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 2·访客 2