A Survey on Reinforcement Learning of Vision-Language-Action Models for Robotic Manipulation

Reimplementation of World-Models (Ha and Schmidhuber 2018) in pytorch

Repository for our paper: Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics

Official PyTorch implementation of the paper: UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training.

Official code of RDT 2

A comprehensive list of papers about dual-system VLA models, including papers, codes, and related websites.

Generate real world ocean, road, and rail routes with reasonable distances all with no dependencies.

[IROS'25] Bio-Inspired Hybrid Map: Spatial Implicit Local Frames and Topological Map for Mobile Cobot Nagivation

Decentralized Simulation Framework designed to integrate multiple advanced physics engines along with various photo-realistic graphics engines to simulate everything

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

Bringing Characters to Life with Computer Brains in Unity

Adversarial skill embeddings for training reusable controllers for physically simulated characters.

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Foundation Models and Data for Human-Human and Human-AI interactions.

A local-first LaTeX & Typst web editor with real-time collaboration & offline support

The open-source CapCut alternative

An extremely fast Python package and project manager, written in Rust.

Deep Learning, an Energy Approach

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

Official repository accompanying a CVPR 2022 paper EMOCA: Emotion Driven Monocular Face Capture And Animation. EMOCA takes a single image of a face as input and produces a 3D reconstruction. EMOCA …

An implementation of local windowed attention for language modeling

[CVPR 2024] Official Implementation of "Seamless Human Motion Composition with Blended Positional Encodings".

This is a implementation of the 3D FLAME model in PyTorch

Mamba SSM architecture

Nvidia GEAR Lab's initiative to solve the robotics data problem using world models

PyTorch code and models for VJEPA2 self-supervised learning from video.

🔥🔥First-ever hour scale video understanding models

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

dreifus lifts your 3D camera experience and facilitates computer vision applications