Stars
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
谷歌新书Agent设计模式(agentic design patterns)中文版，持续更新。附：在线阅读、pdf和epub电子书下载。
A set of ready to use scientific skills for Claude
Maple Mono: Open source monospace font with round corner, ligatures and Nerd-Font icons for IDE and terminal, fine-grained customization options. 带连字和控制台图标的圆角等宽字体，中英文宽度完美2:1，细粒度的自定义选项
An Open-source RL System from ByteDance Seed and Tsinghua AIR
A course on aligning smol models.
Interleaving Reasoning: Next-Generation Reasoning Systems for AGI
The official repository for the paper "ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning"
MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
📖 This is a repository for organizing papers, codes and other resources related to unified multimodal models.
An open-source AI agent that is compatible with multiple LLM models
The ultimate training toolkit for finetuning diffusion models
An open-source AI agent that brings the power of Gemini directly into your terminal.
GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Research code for ECCV 2020 paper "UNITER: UNiversal Image-TExt Representation Learning"
[CoRL '25] Pseudo-Simulation for Autonomous Driving; [NeurIPS '24] NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking
siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems
Python implementation of MPPI (Model Predictive Path-Integral) controller to understand the basic idea. Mandatory dependencies are numpy and matplotlib only.
Official implementation of the paper "GSWorld: Closed-Loop Photo-Realistic Simulation Suite for Robotic Manipulation"
Multi-Joint dynamics with Contact. A general purpose physics simulator.
A visual, interactive outline map that combines the clarity of the outline with the intuitive overview of the minimap. Alternative Minimap.
A modular high-level library to train embodied AI agents across a variety of tasks and environments.
RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots