Qwen/Qwen3-ForcedAligner-0.6B-hf · 仓库更新
模型仓库动态。仓库创建：2026-06-26T08:42:01.000Z。最后修改：2026-06-26T08:42:38.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：token-classification。
接入 API · 个人 AI 解读连接自己的模型解读资讯，浏览新闻无需配置。
GLOBAL AI OBSERVATORY 全球 AI 观察站
AI 资讯雷达紧跟下一次突破。
国内外 AI 最新资讯、大模型发布与能力更新。
追踪 Agent、MCP、算力与显卡，保留原始来源。
60 公开信源6h 更新间隔9 AI 领域
模型 / Agent / 算力 / 硬件 / 安全国内 + 全球
1115 条资讯按来源发布或更新时间排序
Qwen/Qwen-AgentWorld-35B-A3B · 仓库更新
模型仓库动态。仓库创建：2026-06-22T14:49:37.000Z。最后修改：2026-06-25T07:24:16.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：text-generation。
stabilityai/SAME-L · 仓库更新
模型仓库动态。仓库创建：2026-05-17T02:18:14.000Z。最后修改：2026-06-24T20:54:09.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。
Introducing computer use in Gemini 3.5 Flash
来源已更新，查看详情及原始发布记录。
internlm/CapRL-Video-4B · 仓库更新
模型仓库动态。仓库创建：2026-05-22T11:23:34.000Z。最后修改：2026-06-23T02:42:35.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。
Kimi CLI 发布: 1.48.0
## What's Changed * fix(kosong): round-trip empty reasoning content by @RealKai42 in https://github.com/MoonshotAI/kimi-cli/pull/2446 * feat(soul): escalate repeated-tool-call reminders and force-stop on dead-end streak by @jackfish212 in https://github.com/Mo
Kimi CLI 发布: kosong-0.54.0: chore(release): bump kimi-cli to 1.48.0 and kosong to 0.54.0 (#2467)
Co-authored-by: jackfish212 jackfish212@outlook.com
Triton 编译器发布: Triton 3.7.1 Release Notes
Triton 3.7.1 is a patch release on top of 3.7.0. It fixes the following 2 regressions and contains no new features or API changes. ## Regression fixes - Add async read dependencies to FenceAsync — a missing fence between a shared-memory store (st.shared) and a
ByteDance-Seed/Cola-DLM · 仓库更新
模型仓库动态。仓库创建：2026-05-15T07:55:26.000Z。最后修改：2026-06-18T09:28:11.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：text-generation。
PyTorch 发布: PyTorch 2.12.1 Release, bug fix release
This release is meant to fix the following regressions and silent correctness issues: ## Regression fixes - Fix nondeterministic outputs in test_batch_invariance with FLASH_ATTN on NVIDIA B200 GPUs ([#181248](https://github.com/pytorch/pytorch/issues/181248)),
Intel OpenVINO 发布: 2026.2.1
# Summary of improvements * Fixed issue ID 187077: YOLO26 fails to compile on GPU * Resolved an issue in NPU plugin with shared L0 command queue causing violation of app/inference priorities You can find OpenVINO™ toolkit 2026.2.1 release here: * [Download arc
stabilityai/stable-audio-3-medium · 仓库更新
模型仓库动态。仓库创建：2026-05-17T01:50:14.000Z。最后修改：2026-06-16T21:34:14.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：text-to-audio。
Unlocking UK house-building with AI-accelerated planning
UK government partners with Google DeepMind to build a new AI-powered prototype aimed at faster housing decisions.
Securing the future of AI agents
Securing internal systems with an AI Control Roadmap, combining traditional safeguards and real-time monitoring.
AgentScope 发布: v2.0.2
## What's Changed * ci(webui): add format and build checks by @Premsenareddy in https://github.com/agentscope-ai/agentscope/pull/1821 * feat(omni): streaming audio + live captions for DashScope/OpenAI omni by @qbc2016 in https://github.com/agentscope-ai/agents
Transformers 发布: Patch release v5.12.1
# Patch release v5.12.1 Updated the lower bound for PEFT and a fix for auto tokenizer to properly resolve the mistral tokenizer (when `mistral-common` is installed). This is similar to v.5.10.3 minus the fixes that were already included in the main release - v
moonshotai/Kimi-K2.7-Code · 仓库更新
模型仓库动态。仓库创建：2026-06-11T07:51:47.000Z。最后修改：2026-06-15T07:49:29.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：image-text-to-text。
SGLang 发布: v0.5.13.post1
Release v0.5.13.post1
vLLM 发布: v0.23.0
# vLLM v0.23.0 Release Notes Please note that Minimax M3 is not yet supported in this version. Please follow [vLLM recipe](https://recipes.vllm.ai/MiniMaxAI/MiniMax-M3) for usage guides for M3. ## Highlights This release features 408 commits from 200 contribut
SGLang 发布: v0.5.13
## Highlights **New Model Support**: - **Autoregressive**: [Nemotron 3 Ultra](https://docs.sglang.io/cookbook/autoregressive/NVIDIA/Nemotron3-Ultra) (Day-0, [blog](https://www.lmsys.org/blog/2026-06-04-nvidia-run-nemotron-3-ultra/)), [Step-3.7-Flash](https://d
DiffusionGemma: 4x faster text generation
来源已更新，查看详情及原始发布记录。
Investing in multi-agent AI safety research
Google DeepMind and partners announce a $10M funding call for multi-agent safety research.
Fluid, natural voice translation with Gemini 3.5 Live Translate
Gemini 3.5 Live Translate brings near real-time, natural speech translation to Google AI Studio, Google Translate and Google Meet.
Introducing Gemma 4 12B: a unified, encoder-free multimodal model
来源已更新，查看详情及原始发布记录。
Powering the future of robotics in Europe
来源已更新，查看详情及原始发布记录。
CVE-2026-45134: LangSmith SDK: Public prompt pull deserializes untrusted manifests without trust boundary warning
## Description The LangSmith SDK's prompt pull methods (`pull_prompt` / `pull_prompt_commit` in Python, `pullPrompt` / `pullPromptCommit` in JS/TS) fetch and deserialize prompt manifests from the LangSmith Hub. These manifests may contain serialized LangChain
Measuring the impact of learning with AI in Sierra Leone and beyond
Results from a randomized controlled trial show the potential of Gemini’s Guided Learning feature to boost engagement and accelerate learning.
AgentScope 发布: v2.0.1
## Highlight - **Agent Team** is supported ## What's Changed * fix(webui): add missing files in the web ui example by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1661 * fix(readme): update the QR code for DingTalk group by @DavdGao in https://
Kimi CLI 发布: 1.47.0
## What's Changed * fix(tools): include trailing output in error briefs and render brief as plain text by @liruifengv in https://github.com/MoonshotAI/kimi-cli/pull/2389 * docs: rename project to Kimi CLI and link to Kimi Code CLI successor by @RealKai42 in ht
vLLM 发布: v0.22.1
## Highlights This release features 8 commits from 6 contributors (1 new)! v0.22.1 is a patch release on top of v0.22.0 with targeted bug fixes plus a couple of additions: new model support for JetBrains' Mellum v2, zentorch-accelerated quantized linear infere