Official PyTorch Implementation of Unified Video Action Model (RSS 2025)

Official code of Motus: A Unified Latent Action World Model

Light Image Video Generation Inference Framework

Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.

🤖 A curated list of Video Action Models (VAMs) — papers using video generation models to produce executable robot actions. Covers UniPi, UVA, mimic-video, Motus, Cosmos Policy, DreamZero, and more.

[ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

Dimensional is the agentic operating system for physical space. Vibecode humanoids, quadrupeds, drones, and other hardware platforms in natural language and build multi-agent systems that work seam…

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

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Wan: Open and Advanced Large-Scale Video Generative Models

A unified inference and post-training framework for accelerated video generation.

Wan: Open and Advanced Large-Scale Video Generative Models

Helios: Real Real-Time Long Video Generation Model

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

Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization

Official implementation of Continuous 3D Perception Model with Persistent State

Elevate your AI research writing, no more tedious polishing ✨

Causal video-action world model for generalist robot control

Official implementation for pi0 steering via DSRL, Steering Your Diffusion Policy with Latent Space Reinforcement Learning (CoRL 2025)

🔥 Datasets and env wrappers for offline safe reinforcement learning

Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge) (CoRL 2024)

RoboChallenge Inference example code

Multi-Joint dynamics with Contact. A general purpose physics simulator.

🌐 3D and 4D World Modeling: A Survey

[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)