code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models

A collection of GICP-based fast point cloud registration algorithms

Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch

Combining Diffusion Models with PPO to Improve Sample Efficiency and Exploration in Reinforcement Learning

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…

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

[NeurIPS 2024] SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction

[ICLR 2025 Oral] The official implementation of "Diffusion-Based Planning for Autonomous Driving with Flexible Guidance"

An open-source toolbox for fast sampling of diffusion models. Official implementations of our works published in ICML, NeurIPS, CVPR.

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Matterport3D is a pretty awesome dataset for RGB-D machine learning tasks :)

ViPlanner: Visual Semantic Imperative Learning for Local Navigation

iPlanner: Imperative Path Planning. An end-to-end learning planning framework using a novel unsupervised imperative learning approach

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Legged Robot environments for reinforcement learning in Genesis

Robot-centric elevation mapping for rough terrain navigation

A fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives

Isaac Gym Environments for Legged Robots

Elevation Mapping on GPU.

VBD: Versatile Behavior Diffusion for Generalized Traffic Agent Simulation

Fatrop is a nonlinear optimal control problem solver that aims to be fast, support a broad class of optimal control problems and achieve a high numerical robustness.

A generative world for general-purpose robotics & embodied AI learning.

Real-time Whole-body Motion Planning for Mobile Manipulators Using Environment-adaptive Search and Spatial-temporal Optimization (ICRA 2024)