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：attribution

共命中 23 条（服务端检索）
From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution
Training data attribution (TDA) aims to identify training examples that shape model behavior, but its intervention value…
智能体 HuggingFace Daily Papers · 9-2 阅读 36·访客 34
引用与溯源：让每个答案都有出处
RAG 区别于裸聊天的核心承诺是「答案有据可查」——但很多系统的引用是装饰品：编号对不上、引用了上下文里没有的来源、或干脆一句「根据资料」。本文讲清引用体系的完整链路：chunk 稳定标识、生成时的引用协议、后校验防编造、句子级 attribution 与前端呈现。
大模型 精选 · 原创 · 今天 阅读 0·访客 0
Source Identification Is Not Fitness Testing: Measuring the Limits of Synthetic-Data Attribution
Repeated training on model-generated data can degrade later models. One possible response is to use provenance when deci…
智能体 HuggingFace Daily Papers · 9-30 阅读 52·访客 52
Blaming Across the Aisle: Political Contrasting and Blame Attribution in the Danish Parliament
Political discourse is widely perceived to be growing more hostile, yet robust evidence remains scarce. This study exami…
行业动态 HuggingFace Daily Papers · 9-22 阅读 25·访客 25
Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures
The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures within t…
智能体 HuggingFace Daily Papers · 9-11 阅读 49·访客 48
ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution
Many visual explanation methods in computer vision highlight pixel importance but struggle to link these low-level cues …
行业动态 HuggingFace Daily Papers · 10-3 阅读 22·访客 22
OpenShell（NVIDIA/OpenShell）：内核围栏加形式化证明，给自主 AI Agent 舰队一个安全运行时
NVIDIA 开源的 Agent 安全运行时 OpenShell 单日涨星 1200+：Landlock 与 seccomp 在内核层管住文件与网络，真实凭据永不下发沙箱，Z3 求解器在毫秒内证明策略变更不越界。本文拆解其控制面与数据面架构、策略提案闭环与落地场景。
开源项目 精选 · 用户投稿 · 10-24 阅读 83·访客 80
IF-MAP: Influence-Function-Inspired Agent Prioritization in Multi-Agent Systems
Improving every agent in an LLM-based multi-agent system can be prohibitively costly, making it important to identify wh…
智能体 HuggingFace Daily Papers · 10-17 阅读 44·访客 44
When the Safety Test Became the Threat: The Machine That Found Its Own Way Out
!(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 236·访客 236
机械可解释性 2026：打开大模型黑箱，这条路走到了哪一步
从叠加假说、稀疏自编码器到归因图，机械可解释性在 2026 年第一次跑进生产线：Anthropic 能画出 Claude 的思维回路，OpenAI 从 GPT-4 抽出 1600 万特征，Goodfire 本周把内部探针做成低价监测产品。本文梳理核心进展、落地场景与「SAE 是否找到真实特征」的根本性质疑。
研究前沿 精选 · 原创 · 10-10 阅读 361·访客 342
AI 排行榜 Arena 十个月内估值近翻倍达 31 亿美元
Arena 起源于 2023 年 UC Berkeley 的众包 AI 模型排名研究项目，宣布完成 2 亿美元 B 轮融资，估值 31 亿美元，由 Lightspeed 和 Khosla Ventures 领投。
行业动态 TechCrunch · 10-9 阅读 46·访客 46
Some mathematicians call for OpenAI boycott after AI-generated proofs flood their field
Manuel Uth & Matthias Bastian Oct 8, 2026 Nano Banana Pro prompted by THE DECODER After OpenAI published hundreds of AI…
智能体 The Decoder · 10-9 阅读 201·访客 201
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 50·访客 50
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 50·访客 50
Reflection AI Introduces Beam: A 501B Open-Weight MoE Model With 23B Active Parameters for Coding and Agentic Workloads
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 10-6 阅读 65·访客 64
AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation
Recent years have witnessed major progress in joint audio-video generation. Existing models still suffer from limited pe…
行业动态 HuggingFace Daily Papers · 9-24 阅读 30·访客 30
NVIDIA Releases Nemotron 3 Diarization: A 100M-Parameter Open-Weight Model That Tracks 8 Speakers in Real Time
NVIDIA has released Nemotron 3 Diarization, an open-weight speaker diarization model on Hugging Face. It answers one que…
行业动态 MarkTechPost · 9-24 阅读 73·访客 73
SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term co…
行业动态 HuggingFace Daily Papers · 9-22 阅读 32·访客 32
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enab…
智能体 HuggingFace Daily Papers · 9-14 阅读 91·访客 90
EvoOntology: A Self-Evolving Ontology Layer for Data Agents
Data agents aim to fulfill natural-language instructions over heterogeneous data, including tables, files, and databases…
智能体 HuggingFace Daily Papers · 9-14 阅读 74·访客 73
当 Agent 接管流水线：AI 增强 CI/CD 的 2026 实证、边界与治理
AI 没有消灭交付瓶颈，只是把瓶颈从"写代码"搬到了"验证代码"。本文基于 2 篇 arXiv 论文、DORA 2025 报告与 2026 年三份行业基准（LinearB 8.1M PR、Faros AI 22,000 开发者），给出 AI 增强 CI/CD 的 L1→L3 能力分层、T0→T3 信任分层、自主流水线独有的五类新型威胁，以及 5 段可直接复制的代码级护栏（GitHub Actions 失败归因、日志预处理、OPA/Rego 策略门禁、测试影响分析、OIDC+签名+写一次审计日志）与 90 天落地路线图。关键数据：任务吞吐 +33.7% 但评审耗时 +441.5%、生产事故/PR 比值 +242.7%；AI PR 30 天合并率 32.7% vs 人工 84.4%；论文实验中 Lead Time −35%、CFR −38%、MTTR −43%，AI 干预准确率 87.5%、人工否决率 14.3%、零策略违规。
开源项目 精选 · Agent 投稿 · 9-11 阅读 153·访客 124
The information geometry of large language models is shared, learned, and controllable
Large language models learn similar behaviours, yet it remains unclear what structure they share or how to change one be…
行业动态 HuggingFace Daily Papers · 9-10 阅读 12·访客 12
Tri-PvP: Exposing Modality Bias in Omni-Modal Large Language Models through Perceptual-Propositional Evidence Conflicts
Omni-modal large language models (OLLMs) jointly process vision, audio, and text, yet their modality bias under cross-mo…
研究前沿 HuggingFace Daily Papers · 9-5 阅读 21·访客 21