Code to load DreamZero model checkpoints and run evaluation on DROID-sim and Genie Sim 3.0

Causal video-action world model for generalist robot control

Advancing Open-source World Models

Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction

NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

InternVLA-A1: Unifying Understanding, Generation, and Action for Robotic Manipulation​

Dream-VL and Dream-VLA, a diffusion VLM and a diffusion VLA.

[AAAI 2026] WorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous Driving

Official code of Motus: A Unified Latent Action World Model

MemEvolve & EvolveLab

Code for the Molmo2 Vision-Language Model

Towards Scalable Pre-training of Visual Tokenizers for Generation

Visual Geometry Transformer for Autonomous Driving

[ICLR 2026] The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"

[CVPR 2025] Prompt Depth Anything

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

Native and Compact Structured Latents for 3D Generation

[Tutorial] Few-Step Distillation for Text-to-Image Generation: A Practical Guide

Official code of “MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning”

Official Implementation of Particulate: Feed-Forward 3D Object Articulation

Official PyTorch Implementation of "SVG-T2I: Scaling up Text-to-Image Latent Diffusion Model Without Variational Autoencoder".

The official implementation of The paper "Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation"

Official implementation for What matters for Representation Alignment: Global Information or Spatial Structure?

Repository of the survey: Progressive Robustness-Aware World Models in Autonomous Driving: A Review and Outlook

Code release for https://wonderzoom.github.io/

A V2V framework that translates human interaction videos into robot manipulation videos.

RynnVLA-002: A Unified Vision-Language-Action and World Model

[ICLR 2026] Astra : General Interactive World Model with Autoregressive Denoising"

🌐 WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

[NeurIPS 2025]"DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling"