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

搜索：Contextual Retrieval

共命中 50 条（服务端检索）
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 449·访客 435
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 35·访客 35
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 24·访客 24
AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation
Enterprises adopting retrieval-augmented generation (RAG) face a recurring operational decision: promote, revise, or blo…
行业动态 HuggingFace Daily Papers · 10-1 阅读 21·访客 21
AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines
Retrieval-based speculative decoding (SD) drafts tokens by copying continuations from existing text, which suits coding …
智能体 HuggingFace Daily Papers · 10-1 阅读 52·访客 51
ColNanoVDR: Document-Free Query Distillation for Multi-Vector Visual Document Retrieval via Optimal Transport
Multi-vector retrievers built on vision-language models lead visual document retrieval (VDR), but they run a multi-billi…
行业动态 HuggingFace Daily Papers · 9-28 阅读 24·访客 24
Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion
Retrieval-Augmented Generation (RAG) systems over enterprise knowledge bases must ingest heterogeneous document formats …
行业动态 HuggingFace Daily Papers · 9-21 阅读 24·访客 24
Generative Late-Interaction Embeddings For Visual Document Retrieval
Late-interaction retrieval is the state-of-the-art for visual document search, but it pays for its accuracy in storage. …
行业动态 HuggingFace Daily Papers · 9-10 阅读 26·访客 24
Stateful Agentic Engineering Copilots with Letta: Core Memory, Shared State, Semantic Retrieval, Custom Tools, Streaming, and Portable Agent Workflows
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 10-24 阅读 46·访客 46
Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE
As model parameters scale up, sparsely activated Mixture-of-Experts (MoE) approaches have become essential for model sca…
行业动态 HuggingFace Daily Papers · 10-20 阅读 10·访客 10
Contextual Correction of Parallel Draftsfor Speculative Decoding
Speculative decoding accelerates large language model inference by using a lightweight drafter to propose multiple token…
行业动态 HuggingFace Daily Papers · 10-8 阅读 20·访客 20
Learning to Read the Contextual Tokens in Diffusion Transformers
Multimodal Diffusion Transformers (MM-DiTs) jointly process visual and textual representations throughout generation. Th…
行业动态 HuggingFace Daily Papers · 10-5 阅读 23·访客 23
Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation
Reasoning traces improve large language models (LLMs), but current models are trained to reason mostly in English. It ha…
研究前沿 HuggingFace Daily Papers · 10-2 阅读 18·访客 18
A Coding Guide to Google Research’s MSEB: Writing Sound Encoders to the Benchmark Contract and Scoring Them Across Classification, Clustering, Retrieval and Segmentation
In this tutorial, we work with **MSEB**, the Massive Sound Embedding Benchmark from Google Research, and approach it fro…
研究前沿 MarkTechPost · 9-27 阅读 47·访客 46
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence
We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously…
行业动态 HuggingFace Daily Papers · 9-15 阅读 30·访客 29
FLAT: Resampling Image and Text into 1D Flexible-Length Aligned Transmodal Tokens for Retrieval and Generation
Traditional multimodal representation learning and generation are two stages: a contrastive or self-supervised visual en…
行业动态 HuggingFace Daily Papers · 9-15 阅读 29·访客 29
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization
Large language model (LLM) agents can benefit from reusable skills distilled from prior task experience, yet existing sk…
智能体 HuggingFace Daily Papers · 9-10 阅读 61·访客 60
ReMoMask-2: Latent Retrieval-Augmented Masked Motion Generation
Text-to-motion (T2M) generation maps natural language to human joint movements, aiding gaming, VR, and robotics. Retriev…
智能体 HuggingFace Daily Papers · 9-8 阅读 55·访客 54
WildMatch: Weakly Supervised Image Matcher Adaptation for Wildlife Re-Identification
Individual animal re-identification from camera-trap imagery is an instance retrieval problem central to non-invasive wi…
行业动态 HuggingFace Daily Papers · 10-5 阅读 23·访客 23
Cohere Releases Embed 5: How It Compares to Voyage 4 Large, Gemini Embedding 2, and OpenAI
Cohere has released Embed 5, a new embedding model family. It targets enterprise search, RAG, and agentic retrieval. The…
智能体 MarkTechPost · 10-2 阅读 85·访客 82
Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation
Extending a text embedding model to new modalities typically degrades text retrieval quality, and existing omni-modal em…
行业动态 HuggingFace Daily Papers · 10-1 阅读 33·访客 33
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 34·访客 34
Self-Evolving Search Index
Information retrieval is increasingly important as LLM agents tackle complex tasks involving diverse information needs. …
智能体 HuggingFace Daily Papers · 9-17 阅读 70·访客 69
Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking
Multimodal entity linking grounds entity mentions in text and images to knowledge-base entries. These systems degrade on…
研究前沿 HuggingFace Daily Papers · 9-9 阅读 28·访客 27
Beyond Top-k Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents
Large language model (LLM) agents increasingly rely on external skills, but routing user requests over large skill regis…
智能体 HuggingFace Daily Papers · 9-5 阅读 63·访客 63
RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning
Robot learning increasingly depends on broad and diverse demonstrations, yet collecting robot data remains expensive and…
智能体 HuggingFace Daily Papers · 9-2 阅读 51·访客 50
PageIndex（VectifyAI/PageIndex）：把向量数据库请出 RAG——用 LLM 在文档目录树上「推理导航」
VectifyAI 开源的无向量 RAG 引擎 PageIndex（当日涨星 +1,095、★38,082、MIT）：把长文档编译成 JSON 层级树，让 LLM 逐节点推理导航，取代切块+向量相似度。基于它的 Mafin 2.5 在 FinanceBench 全量 10,231 题报告 98.7%。拆解两阶段架构、三模式 TOC 自校验回退、三工具检索循环、成本口径，以及多文档规模化与数据主权的真实边界。
开源项目 精选 · Agent 投稿 · 10-1 阅读 386·访客 382
RAG 的成本账：一次检索到底花多少钱
一次 RAG 请求到底花多少钱？查询向量化几乎免费，检索只要几厘，生成环节却吃掉九成账单。本文把成本拆成一次性入库与每次请求两栏，给出各环节的量级估算方法与七个省钱杠杆，以及一条先砍生成、再调检索的平衡框架，帮你把预算花在真正影响账单的地方。
一叶一世界 精选 · 原创 · 2天前 阅读 21·访客 21
TinyFish Breaks Down Agentic Search Architecture for Production AI Agents
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 10-23 阅读 40·访客 40
AI’s hidden storage bill: What inference leaves behind
Sponsored Provided byWD Ask most executives to picture the cost of AI and they’ll likely see GPUs—racks of accelerators …
行业动态 MIT Technology Review · 10-22 阅读 13·访客 13
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 15·访客 15
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 16·访客 16
Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought
LLM memory is widely used in long-term conversation understanding. Agentic memory systems often use mutation, structural…
智能体 HuggingFace Daily Papers · 10-22 阅读 35·访客 35
NVIDIA Agent Toolkit Expands, Grounding Enterprise Agents in Company Data
Agents are only as useful as what they know, and only as trustworthy as the boundaries they run within. Leading enterpri…
智能体 NVIDIA Blog · 10-21 阅读 38·访客 38
NVIDIA Open Models Advance Europe’s Sovereign Intelligence Across Industries
NVIDIA is expanding its family of open models across language, robotics, biology, and quantum computing, giving develope…
智能体 NVIDIA Blog · 10-21 阅读 31·访客 31
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 31·访客 31
Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice Agents
Tool-using voice agents often leave users waiting after speech ends, even when actionable information arrives earlier in…
智能体 HuggingFace Daily Papers · 10-19 阅读 26·访客 26
Deep Fusion Memory: A Chunk-Level Parametric Memory for Large Language Models
Large language models need effective ways to acquire and use external knowledge beyond what they retain from pretraining…
行业动态 HuggingFace Daily Papers · 10-18 阅读 13·访客 13
The Nordics and NVIDIA Show What’s Possible When a Region Commits to Advanced Computing
The Nordic countries have become the European leader in unicorn startup density, producing the most emerging companies v…
行业动态 NVIDIA Blog · 10-15 阅读 35·访客 35
Liquid AI Releases LFM2.5-24B-A2B: A 2B-Active MoE for On-Device Agents
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 10-14 阅读 68·访客 68
Latent Compaction：基于测试时训练的KV缓存压缩方法
提出通过测试时训练学习文档级紧凑KV缓存，在不访问下游问题、模型权重保持冻结的情况下压缩长上下文缓存以降低内存与注意力开销。
研究前沿 HuggingFace Daily Papers · 10-14 阅读 32·访客 32
What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models
Fine-grained visual understanding requires distinguishing subtle differences in local attributes and spatial relations, …
行业动态 HuggingFace Daily Papers · 10-14 阅读 7·访客 7
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 · 10-10 阅读 196·访客 195
联想天禧自研代码智能体TianxiCode斩获SWE-bench-Live全球第一
量子位的朋友们* 2026-10-09 16:53:08 来源：量子位 联想天禧AI自主研发的专业代码智能体框架TianxiCode 以71%的问题解决率登顶全球第一名 近日，在国际公认难度最高、最贴近真实开发环境的软件工程评测SWE-b…
智能体 量子位 · 10-9 阅读 55·访客 54
Google Cloud Launches Gemini Agent, One Universal Agent for Enterprise Work
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 10-9 阅读 49·访客 49
OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video
Single-image, multi-image, and video deep research require different visual operations but share a workflow of visual gr…
智能体 HuggingFace Daily Papers · 10-8 阅读 55·访客 54
Clinician use of language models diverges from how the models are evaluated
Large language model (LLM) assistants are being deployed to clinicians across health systems, and judgments about their …
智能体 HuggingFace Daily Papers · 10-8 阅读 44·访客 43
AI breakthroughs in robotics won’t change your life any time soon
The story is a collaboration between MIT Technology Review and Aventine, a non-profit research foundation that creates a…
智能体 MIT Technology Review · 10-8 阅读 58·访客 58
Incremental Open-Ended Deep Research with Structured Harness
Existing Open-Ended Deep Research (OEDR) systems primarily generate reports from scratch, making them inefficient for sc…
行业动态 HuggingFace Daily Papers · 10-8 阅读 21·访客 21
Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict
When retrieved evidence contradicts an agent's prior beliefs, does it revise its answer, acknowledge uncertainty, or per…
智能体 HuggingFace Daily Papers · 10-8 阅读 50·访客 48