Stars
Tactile-Aware Manipulation Engine for Closed-Loop Data Collection in Contact-Rich Tasks
WorldEngine: Towards the Era of Post-Training for Physical AI
Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.
Native and Compact Structured Latents for 3D Generation
Semi-automated research assistant for academic research and software development. Supports Claude Code, OpenCode, and Codex CLI across ideation, coding, experiments, writing, and publication.
Code for kai0, including training, inference and data collection.
cuVSLAM: CUDA-Accelerated Visual Odometry and Mapping
PlanT 2.0: Exposing Biases and Structural Flaws in Closed-Loop Driving
[CVPR 2026 Oral] Learning to Drive via Real-World Simulation at Scale
[CVPR'26] LEAD: Minimizing Learner–Expert Asymmetry in End-to-End Driving
Collects papers on autonomous driving E2E learning, VLM/VLA and Hybrid systems, with organized research branches and trends in these fields.
VaViM and VaVAM: Autonomous Driving through Video Generative Modeling (official repository).
Post-training scripts and samples for NVIDIA Cosmos ecosystem
AlpaSim is an open-source autonomous vehicle simulation platform designed for development and testing of end-to-end AV policies
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
[ICRA 2026] Agility Meets Stability: Versatile Humanoid Control with Heterogeneous Data
[NeurIPS 2025] RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning
[ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.
[ICLR 2026] LongLive: Real-time Interactive Long Video Generation
3D Occupancy Prediction Benchmark in Autonomous Driving
123D: A Unified Library for Multi-Modal Autonomous Driving Data
Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)
Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environments.
[NeurIPS 2025 Spotlight] ReSim: Reliable World Simulation for Autonomous Driving
Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
Fast disk usage analyzer with console interface written in Go
[ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".