Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"

Learning Deformable Tetrahedral Meshes for 3D Reconstruction (NeurIPS 2020)

[CVPR 2026 (Oral)] Official Torch/CUDA Implementation of Faithful Contouring

Differentiable Tool for Mesh2Occupancy & Mesh2SDF

⚙️ minimal paralllelizable physics simulator supporting differentiation entirely in torch

Feed-forward model for predicting 3D physics with 3DGS + NeRF

Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.

[CVPR 2026] Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video

[CVPR 2026 Highlight] PhysSkin: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning

Official Code for "GeoPT: Scaling Physics Simulation via Lifted Geometric Pre-Training" https://arxiv.org/pdf/2602.20399

VoMP: Predicting Volumetric Mechanical Property Fields

BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generation Public Code

[SIGGRAPH 2024 & TOG]

Implementation of paper "Uni-3DAR: Unified 3D Generation and Understanding via Autoregression on Compressed Spatial Tokens"

Fast Tetrahedral Meshing in the Wild

Official implementation for "DMesh: A Differentiable Representation for General Meshes" (NeurIPS 2024)

This repository contains the source code and data for Inverse Geometric Locomotion, published at SIGGRAPH 2025.

[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)

[CoRL 2025] Neural Robot Dynamics

[ICCV 2025 Highlight] VolumetricSMPL

ImDy: Human Inverse Dynamics from Imitated Observations (ICLR 2025)

[SIGGRAPH ASIA 2025] This is the official implementation of the SIGGRAPH ASIA 2025 : Hierarchical Neural Semantic Representation for 3D Semantic Correspondence

Nimble: Physics Engine for Biomechanics and Deep Learning

Character Animation Diffusion with Any Topology

Being-VL-0.5: Unified Multimodal Understanding via Byte-Pair Visual Encoding (ICCV 2025, Highlight)

The official implementation of the paper "MAS: Multiview Ancestral Sampling for 3D Motion Generation Using 2D Diffusion"

[CVPR2025] "AniMo: Species-Aware Model for Text-Driven Animal Motion Generation"

Official implementation of Shape My Moves, a framework that generates shape-aware human motions from text by jointly modeling body shape and motion dynamics.

Official repository for "MaskControl: Spatio-Temporal Control for Masked Motion Synthesis" ICCV 2025 (Oral & Award Candidate)