An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Code for MIRA: Multiplayer Interactive World Models with Representation Autoencoders

Our inference and training framework to run on the Cosmos Models

A Comprehensive Survey of Interactive Video World Models

Official implementation of Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation. Accepted in NeurIPS 2025.

WRBench: camera-controlled generation and diagnostic evaluation of video world models.

[Official Code] PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory

A feed-forward 3D foundation model for reconstructing scenes from streaming data

Official Implementation of MultiWorld: Scalable Multi-Agent Multi-View Video World Models

More relighting!

From Automated Idea Factory to Realization

[NeurIPS 2025 D&B🔥] OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

[ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

Interactive World Model papers organized by core research challenges.

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, LTX-2, Qwen Image, Hunyuan Video, LTX Video and Flux.

Official code, models, and data for Vista4D: Video Reshooting with 4D Point Clouds (CVPR 2026 Highlight)

[CVPR 2026 Highlight] VideoCoF: Unified Video Editing with Temporal Reasoner

Karabiner-Elements is a powerful tool for customizing keyboards on macOS

The first open-domain closed-loop revisited benchmark for evaluating memory consistency and action control in world models.

Next-Token Prediction is All You Need

Native Multimodal Models are World Learners

Official repository from the paper "Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind"

(ACM MM 2025) Let Your Video Listen to Your Music! – Beat-Aligned,Content-Preserving Video Editing with Arbitrary Music

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models