Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

AI agents running research on single-GPU nanochat training automatically

A community collection of OpenClaw use cases for making life easier.

omo; the best agent harness - previously oh-my-opencode

Tutorials, Guides and Agent Skills Directories

[NIPS 2025] FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens

CVPR 2025(Highlight) DexGraspAnything: Towards Universal Robotic Dexterous Grasping with Physics Awareness

collection of diffusion model papers categorized by their subareas

A generative world for general-purpose robotics & embodied AI learning.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

[CVPR 2024] LMDrive: Closed-Loop End-to-End Driving with Large Language Models

Official implement for paper "OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries"

✨✨Latest Advances on Multimodal Large Language Models

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

OpenPCSeg: Open Source Point Cloud Segmentation Toolbox and Benchmark

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

An open-source framework for training large multimodal models.

[NeurIPS'23 Spotlight] Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

An open-source tool-augmented conversational language model from Fudan University

[ICCV 2023] Robo3D: Towards Robust and Reliable 3D Perception against Corruptions

Vision-Centric BEV Perception: A Survey

Awesome Lists for Tenure-Track Assistant Professors and PhD students. (助理教授/博士生生存指南)

This is the official code base of VectorMapNet (ICML 2023)

Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation (CVPR 2022)

[PyTorch] Official implementation of CVPR2022 paper "TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers". https://arxiv.org/abs/2203.11496

Code release for ConvNeXt model