Highlights
- Pro
Lists (11)
Sort Name ascending (A-Z)
Stars
Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations https://video-prediction-policy.github.io
The development and future prospects of multimodal reasoning models.
A Modular Toolkit for Robot Kinematic Optimization
[ICLR 2025 Spotlight] Grounding Video Models to Actions through Goal Conditioned Exploration
[CoRL 2024] OrbitGrasp: SE(3)-Equivariant Grasp Learning
The simplest, fastest repository for training/finetuning small-sized VLMs.
Code release for the paper "DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control"
Generative Trajectory Stitching through Diffusion Composition
Decoder Only Transformer Policy for Behavioral Cloning
Official PyTorch Implementation of Habitizing Diffusion Planning for Efficient and Effective Decision Making
Official PyTorch Implementation of "What Makes a Good Diffusion Planner for Decision Making?" [ICLR 2025 Spotlight]
VideoSys: An easy and efficient system for video generation
XLeRobot: Practical Household Dual-Arm Mobile Robot for ~$660
[ICLR 2025] Implementation of Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
The official repo of continuous speculative decoding
Bringing BERT into modernity via both architecture changes and scaling
PARC: Physics-based Augmentation with Reinforcement Learning for Character Controllers
[CVPR 2025 Highlight] InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions
Official Code Implementation for 'A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models'
SkyReels-V2: Infinite-length Film Generative model
Explorations into some recent techniques surrounding speculative decoding
MAGI-1: Autoregressive Video Generation at Scale
Implementing DeepSeek R1's GRPO algorithm from scratch
🚀 Efficient implementations of state-of-the-art linear attention models in Torch and Triton
Muon optimizer: +>30% sample efficiency with <3% wallclock overhead
Source code for the paper DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets