R1-like Computer-use Agent

Project Page For "Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement"

Reproduce R1 Zero on Logic Puzzle

Magic Mirror: ID-Preserved Video Generation in Video Diffusion Transformers

Official Implementation for "Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition"

Official repository for VisionZip (CVPR 2025)

Unified Language-driven Zero-shot Domain Adaptation (CVPR 2024)

Official Codebase of "DiffComplete: Diffusion-based Generative 3D Shape Completion"

MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

[CVPR'25 highlight] RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness

Reference implementation for DPO (Direct Preference Optimization)

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Robust recipes to align language models with human and AI preferences

Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

The official source code for "X-Ray: A Sequential 3D Representation for Generation".

A PyTorch native library for large model training

The official Meta Llama 3 GitHub site

Repo for Rho-1: Token-level Data Selection & Selective Pretraining of LLMs.

Code examples and resources for DBRX, a large language model developed by Databricks

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

[CVPR 2024] GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding