WorldEngine: Towards the Era of Post-Training for Physical AI

🚀 Efficient implementations for emerging model architectures

NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

Reimplementation of LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

Beginner, advanced, expert level Rust training material

AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x.

A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).

[CVPR 2026] Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching

VLA-0: Building State-of-the-Art VLAs with Zero Modification

[RSS 2025] Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks.

[CoRL 2025] Repository relating to "TrackVLA: Embodied Visual Tracking in the Wild"

Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.

[CVPR2025] CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos

An extensible, state-of-the-art framework for columnar compression, and the fastest FOSS columnar file format. Formerly at @spiraldb, now an Incubation Stage project at LFAI&Data, part of the Linux…

Run more RL experiments. Wait less for GPUs.

Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals

GigaWorld-Policy: An Efficient Action-Centered World–Action Model

An interface library for RL post training with environments.

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

On demand communication

This is the official **live** mirror of Ascend-native hardware plugin for ray

Advancing Open-source World Models

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞