[NeurIPS 2024] SceneCraft: Layout-Guided 3D Scene Generation.

GausSurf

Diorama: Unleashing Zero-shot Single-view 3D Scene Modeling (ICCV 2025 Highlight)

[CVPR 2025] RollingDepth: Video Depth without Video Models

[WACV 2025] Official implementation for the paper "Diffusion-based Visual Anagram as Multi-task Learning"

[CVPR 2025 Highlight] Truncated Diffusion Model for Real-Time End-to-End Autonomous Driving

[ICRA, 2025] SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting

Official Repo for the paper "Learning Visual Parkour from Generated Images" (CoRL 2024).

Next-Token Prediction is All You Need

Rotary Transformer

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

Unifying 3D Mesh Generation with Language Models

A fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives

Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation

[NeurIPS 2024 Spotlight] Context and Geometry Aware Voxel Transformer for Semantic Scene Completion

Python inverse kinematics using Pinocchio and QP solvers

Python inverse kinematics based on MuJoCo.

Official implementation of the paper "Hybrid Spatial Representations for Species Distribution Modeling"

[🚀ICML 2025] "Taming Rectified Flow for Inversion and Editing" Using FLUX and HunyuanVideo for image and video editing!

[CoRL 2024 Oral] FREA: Feasibility-Guided Generation of Safety-Critical Scenarios with Reasonable Adversariality

Offical codes for "AutoVFX: Physically Realistic Video Editing from Natural Language Instructions."

Code for "Differentiable Robot Rendering" (CoRL 2024)

[NeurIPS 2024] SCube: Instant Large-Scale Scene Reconstruction using VoxSplats

[ICLR 2024] Official Implementation of Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video