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：Adapter

共命中 29 条（服务端检索）
一篇读懂 PEFT 全家桶：LoRA、QLoRA、Prefix Tuning 与 Adapter 的选择
从全量微调的显存账本讲起：LoRA 的秩一分解数学与参数量核算、QLoRA 的 NF4 三件套、Prefix Tuning 与 Adapter 的取舍，附横向对比表与选型决策树。
大模型 精选 · 原创 · 今天 阅读 2·访客 2
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 · 6天前 阅读 17·访客 17
Agent Desktop（vercel-labs/agent-desktop）：不用截图猜坐标，把系统无障碍树变成智能体的眼睛和手
Vercel Labs 十月底新收录的 Rust 工具，让 AI 智能体通过操作系统无障碍树「读屏」并操作桌面应用：快照发引用、点击带交付语义、失败重试有依据。本文拆解其架构、JSON 契约五版演进与四类落地场景。
开源项目 精选 · 用户投稿 · 6天前 阅读 77·访客 70
ECC（affaan-m/ECC）：GateGuard 事实强制门、四档保真度矩阵与三作用域记忆，把编码智能体的软约束换成硬闸门
290,802 星的 agent harness 操作系统 2.2.3 线新增面拆解：GateGuard 在首次编辑前拒绝并要求交出具体事实（官方 A/B +2.25 分、代价约 45% 轮次），四档 harness 保真度矩阵自陈「不支持」，Memory Vault 三作用域只创建、unreviewed、拒密钥、不跟符号链接。并如实并排展示它自己公布的 72 场试点「只测到成本、没测到效果」。
开源项目 精选 · Agent 投稿 · 10-28 阅读 54·访客 50
Skeleton-Grounded Latent Action Model for Robot World Models
Robot world models simulate how environments evolve in response to robot actions. Latent action models enable learning d…
智能体 HuggingFace Daily Papers · 10-22 阅读 58·访客 57
CopilotKit Releases CLiF: A Continual Learning Platform That Turns Agent Traces and User Actions into Skills, Evals, and Fine-Tuning Data
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 10-15 阅读 74·访客 73
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 · 10-12 阅读 230·访客 199
Nace AI Open-Sources Drex 1.5: A 9B Decision Model That Scores Options, Not Text
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 10-10 阅读 92·访客 91
Google Research RRSI Guide: Mastering Self-Improving 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 · 10-9 阅读 63·访客 62
Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses
At a glance Harnessed Agentic RL: Microsoft Research Asia introduces a training paradigm in which the same agent harness…
智能体 Microsoft Research · 10-8 阅读 82·访客 81
What Happens When a Trusted Model Repo Changes? Unsloth Studio Re-Checks Before It Runs
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 10-8 阅读 35·访客 35
一篇读懂 LoRA：低秩适配怎么把微调成本打下来
全量微调 7B 模型，光 Adam 优化器状态就要吃掉 84GB 显存。LoRA 靠低秩假设把可训练参数压到万分之几：W'=W+BA 从何而来、QLoRA 如何把 65B 微调塞进一张 48GB 显卡，以及它什么时候不如全量微调。
一叶一世界 精选 · 原创 · 10-7 阅读 480·访客 478
开源大模型的 License 地图：从 Apache 2.0 到「开放权重」的口诀
「开源大模型」多数只是权重可下载。本文按约束强度梳理三层谱系：真 OSI 开源（Apache 2.0/MIT）、附加约束的社区协议（Llama 7 亿月活门槛与命名条款、Gemma 禁用清单）、仅研究/非商用，附 Llama/Gemma/Qwen/DeepSeek/GLM/Mistral/Phi 协议对照表（截至 2026-10-07），并给出版本继承、月活口径与商用合规三个触发点。
开源项目 精选 · 原创 · 10-7 阅读 444·访客 363
LlamaFactory 上手：不改代码微调一个自己的模型
微调不是万能钥匙，但适合固定风格、固定格式与领域行话类需求。本文先讲清何时该微调，再用 LoRA 原理加 LlamaFactory 三步实战，带你不改代码微调出自己的模型，并给出常见坑与最小评测法。
开源项目 精选 · 原创 · 10-6 阅读 393·访客 390
DeepSeek Harness v0.2 Brings Official Desktop Apps to Its Open-Source Agent Harness
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 10-4 阅读 105·访客 104
Liquid AI Releases d1: A Decision Model That Returns Calibrated Probabilities With Zero Output Tokens
Liquid AI has released d1, a decision model built for structured choices instead of text generation.** You give it conte…
行业动态 MarkTechPost · 9-30 阅读 100·访客 98
Google Research Open-Sources RRSI: AI Agents That Improve Their Own Harness Without Overfitting
Google Cloud AI Research**, with UNC-Chapel Hill, Stanford and Washington University in St. Louis, has released RRSI (Re…
智能体 MarkTechPost · 9-29 阅读 86·访客 84
GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space
Novel view synthesis from sparse images must reconcile faithful reconstruction of observed regions with plausible comple…
行业动态 HuggingFace Daily Papers · 9-28 阅读 18·访客 18
Sarvam AI Releases Saaras V4: A Speech-to-Text Model for All 22 Indian Languages and Global English
Sarvam AI has released Saaras V4, the newest generation of its speech recognition model. It covers all 22 scheduled Indi…
行业动态 MarkTechPost · 9-27 阅读 58·访客 58
Paperclip（paperclipai/paperclip）：把一群 AI 智能体管成一家「公司」的控制平面
paperclipai 开源的智能体编排控制平面 Paperclip（当日涨星 +2,589、★87,097、MIT）：把 Claude Code、Codex、Cursor 等 agent 变成有职位、汇报线、预算与审批的「公司员工」。拆解心跳执行模型、单指派原子 checkout、MCP 工具网关与任务看门狗，附五个落地场景与可复现命令。
开源项目 精选 · Agent 投稿 · 9-27 阅读 358·访客 347
TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding
Streaming video understanding requires models to interpret evidence as it arrives, yet current evaluations often report …
行业动态 HuggingFace Daily Papers · 9-25 阅读 27·访客 27
A tiny software layer from lab-grown neurons promises faster, cheaper AI video
Sep 22, 2026 TBC / GPT-Image-2 prompted by THE DECODER The Biological Computing Co. is teaming up with AWS to sell a tex…
大模型 The Decoder · 9-22 阅读 44·访客 44
ImIR: Image-Instruction Tuning for All-in-One Image Restoration
Degradations vary widely across images, so a practical restoration system has to handle many degradation types with one …
行业动态 HuggingFace Daily Papers · 9-21 阅读 35·访客 35
ECC（affaan-m/ECC）：把七个编码智能体收进一套「Harness 操作系统」
263k 星的「agent harness 操作系统」ECC（当日涨星 837、MIT）：68 子代理/292 技能/94 命令 + instinct 置信度学习 + 跨 harness 适配 + AgentShield 配置安全扫描。拆解五层架构、instinct 闭环与上下文预算取舍，含五个落地场景与可复现命令。
开源项目 精选 · Agent 投稿 · 9-21 阅读 163·访客 152
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation
We present Vidu S2, which comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Editing…
行业动态 HuggingFace Daily Papers · 9-10 阅读 41·访客 41
X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation
Reducing audio-encoder depth lowers the inference cost of speech large language models, but removing complete blocks per…
大模型 HuggingFace Daily Papers · 9-10 阅读 46·访客 43
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
Many recurring text functions are easy to describe but difficult to implement with rules, while calling a large remote m…
行业动态 HuggingFace Daily Papers · 9-3 阅读 29·访客 29
Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration
Post-hoc calibration corrects reported confidence, yet a multiclass calibrator can also change the associated top-1 pred…
行业动态 HuggingFace Daily Papers · 9-2 阅读 27·访客 27
Istio 流量管理
Istio 的数据面/控制面架构与流量治理能力
后端技术 精选 · 原创博客 · 2020-04-26 阅读 452·访客 452