Code for MIRA: Multiplayer Interactive World Models with Representation Autoencoders

Procedural generation with diffusion models (SIGGRAPH '26)

UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

Text-conditioned infinite worlds in Minecraft

[CVPR26 Oral] MagicBokeh is the first unified method specifically designed for high-zoom bokeh rendering.

[NeurIPS 2025] Official code for Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos

Simulation platform for general-purpose robotics & embodied AI learning.

Comparison of image-to-3D reconstruction methods

[CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs

Code for "EgoX: Egocentric Video Generation from a Single Exocentric Video"

Coherent Human-Scene Reconstruction from Multi-Person Multi-View Video in a Single Pass

An image-to-world skillset for Claude.

C2R: Coarse-to-Real

[ECCV 2026] Official Code of "Distribution Matching Distillation Meets Reinforcement Learning"

A unified framework for easy reinforcement learning in Flow-Matching models

[ICML 2026][Ultra Powerful Few-Step Diffusion RL] TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward

[ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

[ECCV 2026] EgoSim: Egocentric World Simulator for Embodiment Interaction Generation

FDFO: Finite Difference Flow Optimization

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

SR-DiT Speedrunning ImageNet Diffusion

The ultimate training toolkit for finetuning diffusion models

Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow

Kempner Institute Computing Handbook