RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning.

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

High-performance distributed data shuffling (all-to-all) library for MoE training and inference

The seL4 microkernel with loongarch support, see official repositories at https://github.com/seL4

Official Pytorch implementation of the paper "MotionCLIP: Exposing Human Motion Generation to CLIP Space"

An open source implementation of CLIP.

This is the project for Internet-related studies.

My solution to AIVIVN's 5th competition: Server bandwidth prediction

The official implementation of "Divergence of Features and Mean: A BatchNorm-based Abnormality Criterion for Weakly Supervised Video Anomaly Detection"

The seL4 microkernel

2024年计算机保研夏令营&冬令营通知

Official PyTorch implementation of FB-BEV & FB-OCC - Forward-backward view transformation for vision-centric autonomous driving perception

[CVPR 2023] An academic alternative to Tesla's occupancy network for autonomous driving.