A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

MoE training for Me and You and maybe other people

SR-DiT Speedrunning ImageNet Diffusion

Code for "Closing the Train-Test Gap in World Models for Gradient-Based Planning"

TRLC's Development Kit 1

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning

[RSS 2024] 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations

Real-Time VLAs via Future-state-aware Asynchronous Inference.

Unofficial Android companion app for the XTEINK X4

[NeurIPS DB 2025] A gym environment for visual spatial reasoning - knot so simple :)

Async RL Training at Scale

Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence

Code for paper "SPG Sandwiched Policy Gradient for Masked Diffusion Language Models"

hardware design of SO-101 based dual arm robot

Running VLA at 30Hz frame rate and 480Hz trajectory frequency

EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video

Ptera Software is a fast, easy-to-use, and open-source software package for analyzing flapping-wing flight.

Public release of the code for "Accelerating Vision Transformers with Adaptive Patches"

JAX implementation of configurable LLM distillation training

A fork of the official LIBERO benchmark, extended for Hugging Face’s LeRobot integration and large-scale robotics experiments.

Highly accurate and efficient VSLAM system for Python

A Python framework for accelerated simulation, data generation and spatial computing.

VLA-0: Building State-of-the-Art VLAs with Zero Modification

All the source code for "Robot Learning: A Tutorial". Get involved to be featured in the next iteration!