Lists (10)
Stars
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
The official codebase of paper "GMT: General Motion Tracking for Humanoid Whole-Body Control"
Official implementation of SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending
Code for ICML 2025 Paper "Highly Compressed Tokenizer Can Generate Without Training"
PyTorch code and models for VJEPA2 self-supervised learning from video.
A list of works on video generation towards world model
Official repository for "CompilerDream: Learning a Compiler World Model for General Code Optimization" (KDD 2025), https://arxiv.org/abs/2404.16077
Official repository for "Trajectory World Models for Heterogeneous Environments" (ICML 2025), https://arxiv.org/abs/2502.01366
[ICRA 2024]: Train your parkour robot in less than 20 hours.
Code for Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes (Science Robotics)
[CoRL 2024] HumanPlus: Humanoid Shadowing and Imitation from Humans
Various retargeting optimizers to translate human hand motion to robot hand motion.
Open-source Multi-agent Poster Generation from Papers
Official Implementation of "Sampling-Based System Identification with Active Exploration for Legged Robot Sim2Real Learning"
A paper list of some recent works about Token Compress for Vit and VLM
A curated list of awesome work on VAEs, disentanglement, representation learning, and generative models.
Official repository for "RLVR-World: Training World Models with Reinforcement Learning", https://arxiv.org/abs/2505.13934
Unfied World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
Best Papers of Top Venues like CVPR, NeurIPS, ICLR, ICML, ICCV, ECCV, ...
Analyzing Instant Messaging (IM) applications transportation. Code based on the academic paper "Practical Traffic Analysis Attacks on Secure Messaging Applications"
[SIGGRAPH 2025] SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations
Interactive visualizations of the geometric intuition behind diffusion models.