Official implementation of Click-and-Traverse

Official implementation of Any2Track.

Official implementation of OpenWBT.

[NeurIPS 2025 Spotlight] SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation

Official repository of "TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding".

Official repository of "CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement".

[ECCV'24] Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfer

[ICLR 2024 Spotlight] DreamLLM: Synergistic Multimodal Comprehension and Creation

[ICLR 2023] Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance

[CVPR'23] JacobiNeRF: NeRF Shaping with Mutual Information Gradient

CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesis

[CVPR2023]Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning

[ICLR 2023] Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?

[ICML 2023] Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining

The official instructions of HOI4D dataset.

[ICCV 2021] "HPNet: Deep Primitive Segmentation Using Hybrid Representations"

Adversarial Texture Optimization from RGB-D Scans (CVPR 2020).

path invariance map network research project

Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion