Stars
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
【三年面试五年模拟】AIGC算法工程师面试秘籍。涵盖AIGC、LLM大模型、AI Agent、传统深度学习、自动驾驶、机器学习、计算机视觉、自然语言处理、强化学习、大数据挖掘、具身智能、元宇宙、AGI等AI行业面试笔试干货经验与核心知识。
CompassAD: Intent-Driven 3D Affordance Grounding in Functionally Competing Objects
StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx
A generative world for general-purpose robotics & embodied AI learning.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...)…
verl: Volcano Engine Reinforcement Learning for LLMs
🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT！🌏 Train a 64M-parameter GPT from scratch in just 2h!
✨✨Latest Advances on Multimodal Large Language Models
My learning notes for ML SYS.
[ICML 2025] Official code for the paper 'DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space'
Awesome collection of resources and papers on Diffusion Models for Robotic Manipulation.
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.
🌟100+ 原创 LLM / RL 原理图📚，《大模型算法》作者巨献！💥（100+ LLM/RL Algorithm Maps ）
[CVPR 2026] Official implementation of "ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models"
Code implementation of the paper "World-in-World: World Models in a Closed-Loop World" (ICLR'26 Oral)
Fully open reproduction of DeepSeek-R1
你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.
Reference PyTorch implementation and models for DINOv3