Stars
Fast CUDA implementation of (differentiable) soft dynamic time warping for PyTorch
[CVPR25 Oral (Top 3.3%)] Official code for paper "Reconstructing Humans with a Biomechanically Accurate Skeleton".
[CVPR 2025 Oral] TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization
BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO
The official implementation of the paper "Human Motion Diffusion as a Generative Prior"
OmniControl: Control Any Joint at Any Time for Human Motion Generation, ICLR 2024
The official PyTorch implementation of the paper "Human Motion Diffusion Model"
MANO hand model in PyTorch (anatomy consistent, anchors, etc)
4DHumans: Reconstructing and Tracking Humans with Transformers
HaMeR: Reconstructing Hands in 3D with Transformers
High-resolution models for human tasks.
Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos
C++ TensorRT implementation of Depth-Anything V1, V2
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
[NeurIPS 2023] Official Code for "SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation"
Official implementation of `Splatter Image: Ultra-Fast Single-View 3D Reconstruction' CVPR 2024
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
A Python nearest neighbor descent for approximate nearest neighbors
This repository contains demos I made with the Transformers library by HuggingFace.
🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.
An efficient single/multi-agent trajectory planner for multicopters.