#
Lists (13)
Starred repositories
Official Implementation of "KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skill 10000 s"
PyTorch code and models for VJEPA2 self-supervised learning from video.
RoboDual: Dual-System for Robotic Manipulation
This is an open-source version of the representation engineering framework for stopping harmful outputs or hallucinations on the level of activations. 100% free, self-hosted and open-source.
VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework
huggingface / yourbench
Forked from sumukshashidhar/yourbench🤗 Benchmark Large Language Models Reliably On Your Data
遇事不决，Vibe 力学! One-Person Company AI Tools Series – continuously updated to help boost productivity and empower your solo business!
A Datacenter Scale Distributed Inference Serving Framework
Roblox Foundation Model for 3D Intelligence
A generative world for general-purpose robotics & embodied AI learning.
[CVPR 2025] Source codes for the paper "3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning"
DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping
VaViM and VaVAM: Autonomous Driving through Video Generative Modeling (official repository).
The python library for real-time communication
[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling
Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体！
Data-Driven Astrology 💫 Kerykeion is a Python library for astrology. It generates SVG charts and extracts detailed structured data for birth charts, synastry, transits, composite charts, and more.
Quickly produce both human-readable and JSON-formatted astrology chart data based on the Swiss Ephemeris and astro.com.
Clone a voice in 5 seconds to generate arbitrary speech in real-time
Open-source framework for all AI agents.
LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.