AI
AI 资讯
alishangtian.com
主题色 · THEME
提交线索
anthropicopenaiagenthuggingface daily papersai安全jake whartongpuit之家solidot港股

搜索：vectorize-io

共命中 50 条（服务端检索）
Hindsight（vectorize-io/hindsight）：让智能体「学会」而不只是「记住」的记忆架构
Vectorize 开源的智能体记忆系统 Hindsight（当日涨星 +4,463、★37,121、MIT）：以世界事实/经验/观察/心智模型四网络替代扁平 RAG，LongMemEval 从同骨干全上下文的 39.0% 拉到 83.6%、最强 91.4%。拆解 TEMPR/CARA 分层、四路检索+RRF+重排、反思持久化机制，附五个落地场景与竞品争议。
原创 开源项目 Agent 投稿 精选 · 今天 阅读 3 · 访客 3
Epoll原理
IO 多路复用演进：select/poll 到 epoll 的事件驱动模型
原创 后端技术 原创博客 精选 · 2020-04-22 阅读 27 · 访客 27
Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
Diffusion Large Language Models (dLLMs) have recently emerged as a promising alternative to autoregressive LLMs by enabl…
大模型 HuggingFace Daily Papers 6天前 阅读 3 · 访客 3
Agent-Native（BuilderIO/agent-native）：让 UI 与智能体共用一个「动作层」
Builder.io 开源的 agentic 应用框架（当日涨星 607、★5,838、MIT）：一份 defineAction 同时成为智能体工具、React hook、HTTP、MCP、A2A 与 CLI，权限六开关 + 审批 + 审计全调用面生效。拆解动作层架构、约 40 个停止条件的运行时与五个落地场景。
原创 开源项目 Agent 投稿 精选 · 6天前 阅读 47 · 访客 43
一文读懂Kafka高可用设计
Kafka 的分区、副本机制与高性能 IO 设计
原创 后端技术 原创博客 精选 · 2020-05-19 阅读 31 · 访客 31
零拷贝
从 sendfile 到 mmap：零拷贝如何减少上下文切换
原创 后端技术 原创博客 精选 · 2020-04-21 阅读 45 · 访客 44
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 昨天 阅读 4 · 访客 4
AI access makes people almost entirely unwilling to say "I don't know," study finds
Sep 26, 2026 Nano Banana Pro prompted by THE DECODER Researchers ran five experiments with 3,132 participants to test wh…
行业动态 The Decoder 昨天 阅读 5 · 访客 5
Some Supabase customers are publicly exposing reams of people’s data to the web
Thousands of databases hosted by development platform Supabase are exposing people’s sensitive information to the public…
行业动态 TechCrunch 2天前 阅读 4 · 访客 4
I created an interactive digital avatar of myself — and you can talk to it
When Alexandru Voica, head of corporate affairs at the video-generation startup Synthesia, sent me a link this summer to…
行业动态 TechCrunch 2天前 阅读 2 · 访客 2
笔记本跑7000亿参数GLM！无GPU也行? SSD当显存用火爆GitHub
田, 晏林* 2026-09-26 17:01:00 来源：量子位 GitHub现在最火热的大模型开源小蜂鸟Colibrì是个啥？ 闻乐 发自 凹非寺 量子位 | 公众号 QbitAI 25GB笔记本硬跑744B GLM-5.2，32GB…
开源项目 量子位 2天前 阅读 5 · 访客 5
End-to-End Multimodal Data Augmentation and Adversarial Robustness Benchmark with AugLy for Images, Text, Audio, and PyTorch
In this tutorial, we build a comprehensive multimodal augmentation and robustness workflow with **AugLy** for images, te…
研究前沿 MarkTechPost 2天前 阅读 1 · 访客 1
Black Forest Labs Releases FLUX 3 Action: A 7B Open-Weights World Action Model That Tops RoboLab-120
Black Forest Labs (BFL), the lab behind the FLUX image models, has released FLUX 3 Action. It is a 7B open-weights World…
智能体 MarkTechPost 3天前 阅读 3 · 访客 3
Perplexity Trains Its Computer Agent on Real Mistakes With Hint-Guided Self-Distillation
Perplexity Research published a new post-training study. It trains a model inside Perplexity Computer on real user sessi…
智能体 MarkTechPost 3天前 阅读 4 · 访客 3
教机器人干活，光“刷课时”可不够！灵初这次较真数据质量
思邈* 2026-09-24 13:45:20 来源：量子位 专治人机动作对不齐 允中 发自 凹非寺 量子位 | 公众号 QbitAI 教机器人干活的“人类示范”，竟然不是人做的？ 看这组对照视频：一边是人手操作，一边是机械手操作。乍一看…
行业动态 量子位 4天前 阅读 9 · 访客 9
Google's new Flash TTS models let you design AI voices from scratch using text descriptions
Sep 23, 2026 Nano Banana Pro prompted by THE DECODER Key Points Google has released two new text-to-speech models, Gemin…
大模型 The Decoder 4天前 阅读 21 · 访客 20
5分钟完成机器人纳管、10秒启动跨集群任务，清华大学联合无问芯穹开源具身智能云原生平台RLark
量子位的朋友们* 2026-09-24 13:19:55 来源：量子位 开源一座具身智能的新“塔台” 一架架飞机在空中有序飞行，按时起降，看似只是飞机自己的事情，实际上，它需要持续与机场、跑道、航线以及地面资源系统协同。 这正是“塔台”存…
开源项目 量子位 4天前 阅读 8 · 访客 8
Offloaded inference for real-world physical AI robotics
At a glance Challenges a core assumption in robotics AI: Our research shows that running physical AI inference exclusive…
智能体 Microsoft Research 4天前 阅读 16 · 访客 16
DeltaWAM: Delta World Action Models for Bimanual Manipulation
World-action models (WAMs) transfer visual and motion priors from pretrained video generators to robot control by jointl…
智能体 HuggingFace Daily Papers 5天前 阅读 2 · 访客 2
SpeakON Ships a MagSafe AI Voice Button With Its Own Microphone
Voice input on phones has been solved for years. What has not been solved is the output. Speak into most dictation tools…
行业动态 MarkTechPost 5天前 阅读 3 · 访客 3
AX（google/ax）：把智能体当成集群工作负载——Google 开源的 Agent 执行编排运行时
Google 开源的智能体执行编排运行时 AX（当日涨星 2,324、★7,482、Apache-2.0）：四个原语 Task/Workspace/Gateway/Model，把智能体变成可 apply/watch/suspend/resume 的集群负载。拆解控制面（Redis Streams 队列）、runner 契约、出网围栏与生成式 workspace，并给出预算失控、退出码不回读等七项风险与五个落地场景。
原创 开源项目 Agent 投稿 精选 · 5天前 阅读 49 · 访客 45
NVIDIA Isaac ROS 5.0 Advances Agentic, Open Source Robotics Development
To build and deploy sophisticated robotics applications that can perceive, reason and act in dynamic environments, devel…
智能体 NVIDIA Blog 6天前 阅读 7 · 访客 7
Alibaba Qwen Releases Qwen-Image-2.1: A 7B Open-Weight Model for Image Generation and Editing
Alibaba's Qwen team has released Qwen-Image-2.1, a 7B diffusion transformer that handles text-to-image generation, multi…
大模型 MarkTechPost 6天前 阅读 22 · 访客 22
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 6天前 阅读 14 · 访客 13
AWS Strands Agents Team Releases Strands Harness: An Open-Source Agent Harness With 28% Lower Token Cost at Comparable Accuracy
Many developers find that an agent idea works inside Claude Code or Codex, then struggles once they rebuild it with thei…
智能体 MarkTechPost 6天前 阅读 25 · 访客 25
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 6天前 阅读 8 · 访客 8
深度研究｜Meta Muse 全解：个人智能体的分水岭产品，与「可审计 Agent 运行环境」的标准答案
基于 2026-09-22 独立研究整理：拆解 Meta Muse 的三层产品谱系与时间线、Secure VM 六层防护（凭据代理替换 / tainted egress / 审批绕过模型）、Muse Spark 1.3 能力口径（AA 指数 61–62 vs Claude Fable 5.1 的 66）、定价与商业模型、三情景推演与风险矩阵，并给出核心判断——Agent 的天花板由平台开放意愿决定，而非模型智力。
原创 智能体 Agent 投稿 精选 · 6天前 阅读 183 · 访客 167
GPT-6 Astra开进机器人身体！清华联手无问芯穹等开源RPent
在物理世界真正干活的具身智能体]
智能体 量子位 9-21 阅读 19 · 访客 19
Best Voice Cloning APIs in 2026: Speaker Similarity, Consent Checks, and Price per 1M Characters
We cloned one 10-second voice on 7 platforms and ranked them on reference audio, consent, licensing, and cost. The post …
行业动态 MarkTechPost 9-21 阅读 11 · 访客 11
RULER: Instance-aware Rubric Rewards for SVG Generation
Generating Scalable Vector Graphics (SVG) code from natural-language instructions is an open-ended task without absolute…
智能体 HuggingFace Daily Papers 9-21 阅读 4 · 访客 4
Tencent's Gander aims to keep talking while it works in the background
Tencent's Gander processes speech, images, and text while handling tasks in the background. A "cerebellum" keeps the con…
行业动态 The Decoder 9-20 阅读 8 · 访客 8
GGUF vs GPTQ vs AWQ vs EXL2: LLM Model Formats Explained (2026)
GGUF, GPTQ, AWQ, EXL2, and EXL3 solve the same problem in different ways. This guide separates file containers from quan…
大模型 MarkTechPost 9-19 阅读 25 · 访客 23
UltraTex: Unleashing 2K Multi-View Diffusion for 3D Texturing
High-quality texture generation is essential for creating realistic and production-ready 3D assets. Recent multi-view di…
行业动态 HuggingFace Daily Papers 9-19 阅读 0 · 访客 0
Microsoft Open-Sources TauGrid: A Kubernetes-Native Stack for GPU AI Workloads
Microsoft's AKS engineering team open-sourced TauGrid on August 28, 2026, packaging the tau CLI, Kueue queueing, KubeRay…
开源项目 MarkTechPost 9-18 阅读 22 · 访客 22
OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue
We define OmniVChat (Omni Video Chat) as the task of native audio-visual dialogue between a user and an omni model. In O…
研究前沿 HuggingFace Daily Papers 9-18 阅读 10 · 访客 9
APort Vault: Benchmarking AI Agent Payment Authorization with the Open Agent Passport
APort Vault is a benchmark for payment authorization in tool-using AI agents. It replays 4,371 attacks written by humans…
智能体 HuggingFace Daily Papers 9-18 阅读 8 · 访客 7
IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts
Mixture-of-Experts (MoE) scales capacity, but existing designs cannot set three quantities independently. For a single t…
行业动态 HuggingFace Daily Papers 9-18 阅读 7 · 访客 7
From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention
A pretrained robot foundation policy may execute most of a long-horizon task yet repeatedly fail at a few critical subta…
智能体 HuggingFace Daily Papers 9-18 阅读 5 · 访客 5
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
Training capable coding agents via reinforcement learning (RL) requires diverse tasks with reliable verifiers. Open-sour…
智能体 HuggingFace Daily Papers 9-18 阅读 9 · 访客 8
HuRo: Robotizing Human Videos for Scalable VLA Pretraining
Human video datasets offer an abundant and diverse source of interaction data that can complement expensive real-robot d…
智能体 HuggingFace Daily Papers 9-18 阅读 2 · 访客 2
OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation
Reference-to-video (R2V) generation is evolving toward increasingly general and versatile reference control, giving rise…
研究前沿 HuggingFace Daily Papers 9-18 阅读 9 · 访客 9
The fix for rogue AI agents could be more AI
As companies hand off longer and more complex tasks to AI agents, they are running into an oversight problem: Agents can…
智能体 TechCrunch 9-18 阅读 16 · 访客 15
RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents
Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development throug…
智能体 HuggingFace Daily Papers 9-18 阅读 9 · 访客 9
Stanford Researchers Release Paper2Agent: Turning Research Papers Into AI Agents That Reproduce Results and Run on New Data
Paper2Agent, published in Nature, converts papers into validated MCP tools, scoring 91.2% on 300 questions across 74 pap…
智能体 MarkTechPost 9-17 阅读 21 · 访客 21
Al Gore says the real AI risk isn’t data centers
In an interview with TechCrunch, Al Gore suggested he isn't losing sleep over AI data center emissions — he's more worri…
行业动态 TechCrunch 9-17 阅读 11 · 访客 11
WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing
Document parsing converts document images into structured content and requires reliable performance across diverse layou…
行业动态 HuggingFace Daily Papers 9-17 阅读 12 · 访客 11
TeleAntiFraud 2.0: A Refreshable, Profile-Grounded, and Audio-Based Benchmark for Telecom Fraud Detection
Telecom fraud scripts evolve rapidly and are often designed to resemble routine service conversations, creating two key …
研究前沿 HuggingFace Daily Papers 9-17 阅读 7 · 访客 7
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation
We study length inflation in on-policy distillation (OPD), where student responses can become excessively long and even …
行业动态 HuggingFace Daily Papers 9-17 阅读 17 · 访客 16
DeformSmith: Physics Harness-Guided Hierarchical Generation of Deformable Assets for Robot Manipulation
Creating deformable assets for robot manipulation requires jointly specifying their geometry, appearance, and physical p…
智能体 HuggingFace Daily Papers 9-17 阅读 6 · 访客 6
FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
Modeling articulated objects from sparse monocular views is challenging because each observation reveals only partial ge…
行业动态 HuggingFace Daily Papers 9-17 阅读 14 · 访客 13