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

AI agents running research on single-GPU nanochat training automatically

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

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

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

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

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

Code release for ConvNeXt model

An open-source framework for training large multimodal models.

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

Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)

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

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

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

OpenPCSeg: Open Source Point Cloud Segmentation Toolbox and Benchmark

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

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

[CVPR 2021/TPAMI 2023] Rank 1st in the public leaderboard of SemanticKITTI Panoptic Segmentation (2020-11-16)

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

[ NeurIPS 2021 ] Pytorch implementation for "Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion"

[CVPR 2021] Instance Localization for Self-supervised Detection Pretraining

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

Code for our CVPR19 -- "Adapting Object Detectors via Selective Cross-Domain Alignment"

SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds (ECCV2020)

Unsupervised learning of Object Landmarks through Conditional Image Generation

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