Stars
[CVPR 2025 Oral] VGGT: Visual Geometry Grounded Transformer
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
[ACM MM 2023] Official implementation of paper "Language-guided Human Motion Synthesis with Atomic Actions".
Numerical Inverse Kinematics solver based on JAX + MJX
Hiera: A fast, powerful, and simple hierarchical vision transformer.
[AAAI 2025] Official Repository of 'SKI Models: Skeleton Induced Vision-Language Embeddings for Understanding Activities of Daily Living'
A python library to facilitate interaction with Onshape's REST API
verl: Volcano Engine Reinforcement Learning for LLMs
Minimal reproduction of DeepSeek R1-Zero
Official PyTorch Implementation for Paper "No More Adam: Learning Rate Scaling at Initialization is All You Need"
pytorch implementation of the different DeepGaze models
[CVPR 2025] SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting
Library for reading and processing ML training data.
Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"
JAX implementation of the T5 model: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
OpenTAD is an open-source temporal action detection (TAD) toolbox based on PyTorch.
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
[3DV'25] 3D Reconstruction with Spatial Memory
[NeurIPS 2024 Spotlight] Implementation of the paper "3D Gaussian Splatting as Markov Chain Monte Carlo"
Code of the paper "LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning" & LocoMuJoCo Baselines