Dépôts Machine learning en tendance

We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.

Learn AI Engineering! Learn it. Build it. Ship it for others.

Turn world-model imagination into corrective training data for robot policies — a single-GPU, falsifiable pipeline (SmolVLA · LIBERO · CEM · paired simulator replays).

Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.

Iris-3B: pixel-space generation & general vision learner. A 3B diffusion transformer that generates every pixel directly (no VAE); the same prior, fine-tuned, does monocular depth estimation and 4x image restoration. Paper, weights, training code and demo.

Interactive, source-linked ML workflow diagrams written by your coding assistant (Copilot, Codex or Claude Code) and opened in VS Code.

深度学习与强化学习的系统学习路线：38 个实验，每个配数学推导笔记、原创插图和从零实现的代码

YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

四十五门真实网课的模块合辑全书 + 思维导图复习笔记 + 逐字稿，全部由 Video2Book 从课程音频重构：518 册教材、603 篇笔记、2,286 份逐字稿，从逐讲精读到考前速查，笔记支持 Markmap / XMind 脑图导入。

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

收录最全、更新最快的技能Skills商店：精选原创技能包（涵盖文档处理、内容创作、编程开发、机器学习、自动化工作流），全部打包好可直接安装使用！同时自动抓取GitHub上万个Skills项目，按分类、更新时间、Star数量整理。The most comprehensive and frequently updated AI Agent skill library, featuring curated skill packs across document processing, content creation, programming, machine learning, automated workflows, and many more domains.

A small, fast decision model, or system one model, for agentic workflows. Pick between options or rate on a scale faster than an LLM, with a calibrated confidence on every decision.

Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images

本地优先的全栈 AI 创作工作站：AI对话 · AI漫画 · 漫剧创作 · 写作台 · 知识学习五大模块；vLLM / llama.cpp / Transformers 多引擎本地推理，显存智能调度、舱壁隔离自愈、仅供学习使用，欢迎交流指正。（最新进度（除插件系统）受到协议限制，暂时无法提交到仓库）

My Python scripts to make high-quality figures for publications in top AI conferences and journals.

PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers

Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~165 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code, Codex, opencode and pi.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.