Starred repositories
BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx
First Latency-Aware Competitive LLM Agent Benchmark
Code for ICCV'2025 "RayZer: A Self-supervised Large View Synthesis Model"
MAGI-1: Autoregressive Video Generation at Scale
Official implementation for WorldScore: A Unified Evaluation Benchmark for World Generation
Official PyTorch implementation of FlowMo.
Official PyTorch implementation of One-Minute Video Generation with Test-Time Training
[ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"
Reconstructs Minecraft builds from screenshots + parallelized ray-tracing rendering
High-performance C++ library for multiphysics and multibody dynamics simulations
Using message app/bot to notify you when doing time-consuming tasks. Bake your experiments!
A Blender add-on for importing a sequence of OBJ meshes as frames
(CVPR 2025 Highlight) The Scene Language: Representing Scenes with Programs, Words, and Embeddings
✨ Reverse-engineered Python API for Google Gemini web app
[CVPR 2025] WildAvatar: Learning In-the-wild 3D Avatars from the Web
[NeurIPS 2024] Official code for "Neural Gaffer: Relighting Any Object via Diffusion"
[NeurIPS 2024] GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling
[ICML 2022] Official PyTorch implementation of the paper "Unsupervised Image Representation Learning with Deep Latent Particles"
Unofficial implementation of "Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting", ECCV2024.
[CVPR 2024] Official repository for "Tactile-Augmented Radiance Fields".
Lightplane implements a highly memory-efficient differentiable radiance field renderer, and a module for unprojecting features from images to 3D grids.
[AAAI 2025] DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors