LLaDA2.0-Uni: Understanding and Generation the World.

分享AI Infra知识&代码练习：PyTorch/vLLM/SGLang框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等

Awesome List for On-Policy Distillation

A unified framework for easy reinforcement learning in Flow-Matching models

X-Voice

将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿，你的 AI 科研副导师。

Practical, Colab-friendly notebooks for fine-tuning and running audio AI models

Pipeline to help users extract content from long meeting recordings.

😼 优雅地使用基于 clash/mihomo 的代理环境

Language modelling on RVQ tokens with minimal codes

Nano vLLM

Awesome Multimodal Modeling [Covers MLLM, UMM, and NMM]

Some comprehensive papers about speaker diarization

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

A framework for efficient model inference with omni-modality models

Hy3 preview (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency

X-VC: Zero-shot Streaming Voice Conversion in Codec Space

科研写作助手 (Research Writing Assistant)

Repository for training models for music source separation.

Text-to-text alignment algorithm for speech recognition error analysis.

VS Code 配置 LaTeX 进行高效论文写作

The project page of DiTReducio (Accepted by ACL 2026 Findings)

🎓 上海交通大学全能 AI 助手 — 基于 OpenClaw 的交大校园 Skill 包 | 19项功能覆盖 DDL/选课/邮箱/食堂/图书馆/PPT生成

Claude Code+Obsidian，邪修读论文就是快

High-Quality Voice Cloning TTS for 600+ Languages

💥 Blazing fast terminal file manager written in Rust, based on async I/O.

Parameter-efficient text-to-audio generation for edge and low-memory deployment.