News

I gave an invited talk at the Datapalooza 2025.

Our work PUFM: Efficient Point Cloud Upsampling via Flow Matching has been accepted by AAAI 26.

I will give keynote talks at two workshops at ICCV 2025: 2nd Edition of Workshop on Foundation Models for V2X-Based Cooperative Autonomous Driving and 1st Workshop on Generating Digital Twins from Images and Videos.

I will serve as an Area Chair for CVPR 2026.

I joined the School of Data Science at the University of Virginia as a tenure-track Assistant Professor.

Our work DiffuMatch: Category-Agnostic Spectral Diffusion Priors for Robust Non-rigid Shape Matching has been accepted by ICCV 2025.

Our work MeshPad: Interactive Sketch-Conditioned Artist-Reminiscent Mesh Generation and Editing has been accepted by ICCV 2025.

I was invited to serve as a member of the program committee for Pacific Graphics 2025.

Our work MeshArt: Generating Articulated Meshes with Structure-Guided Transformers has been accepted by CVPR 2025.

Our work LT3SD: Latent Trees for 3D Scene Diffusion has been accepted by CVPR 2025.

I was invited to serve as a member of the international program committee for Shape Modeling International 2025.

I was invited to serve as a member of the international program committee for Eurographics Symposium on Geometry Processing 2025.

Our work To Supervise or Not to Supervise: Understanding and Addressing the Key Challenges of Point Cloud Transfer Learning has been accepted by ECCV 2024.

I was invited to serve as a member of the Full Papers International Program Committee for Eurographics 2025.

I gave a talk, titled Empowering Machines with Deeper Shape Understanding, at the first CS Schnupperstudium Event for Women organized by Technical University of Munich.

Our work GenZI: Zero-Shot 3D Human-Scene Interaction Generation has been accepted by CVPR 2024.

I was invited to serve as a member of the Technical Papers Committee for Eurographics Symposium on Geometry Processing 2024.

I gave an invited talk, titled Towards Robust Shape Correspondence: Learning with Receptive Field Optimization, in the Group of Geometric Computation and Visualisation led by Prof. Shengjun Liu at Central South University, China.

Postdoc at 3D AI Lab, Technical University of Munich.

Our work Generalizable Local Feature Pre-training for Deformable Shape Analysis has been accepted by CVPR 2023 and selected as a highlight (10% of accepted papers, 2.5% of submissions).

I gave an invited talk, titled Towards Robust Geometric Deep Learning for Shape Correspondence, as part of the Dell Technical Generations Series Talk organized by Dell Technologies, Shanghai.

I gave a poster presentation of our work SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondence, at the first Hi! PARIS Meet Up event.

Our work Learning Multi-resolution Functional Maps with Spectral Attention for Robust Shape Matching has been accepted by NeurIPS 2022.

Our work SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondence has been accepted by 3DV 2022.

Our work WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registration has been accepted by IEEE Transactions on Visualization and Computer Graphics.

Our work PointDSC: Robust Point Cloud Registration Using Deep Spatial Consistency has been accepted by CVPR 2021.

Postdoc at LIX, École Polytechnique / Inria.

Our work Fast Sketch Segmentation and Labeling with Deep Learning is the runner-up for the 2019 Best Paper Award from IEEE Computer Graphics & Applications by the IEEE Computer Society Publications Board.

Our work SketchDesc: Learning Local Sketch Descriptors for Multi-View Correspondence has been accepted by IEEE Transactions on Circuits and Systems for Video Technology.

Ph.D. thesis defence.

I gave an invited talk, titled End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds, at LIX, École Polytechnique / Inria.

Our work Sketch-R2CNN: An RNN-Rasterization-CNN Architecture for Vector Sketch Recognition has been accepted by IEEE Transactions on Visualization and Computer Graphics.

Our work End-to-End Learning Local Multi-View Descriptors for 3D Point Clouds has been accepted by CVPR 2020.

Internship at Megvii Research. Advised by Dr. Jue Wang.

Our work Fast Sketch Segmentation and Labeling with Deep Learning has been accepted by IEEE Computer Graphics & Applications.

Our work Context-based Sketch Classification has been accepted by Expressive 2018.

Internship at Alibaba A.I. Labs. Advised by Dr. Siyu Zhu and Prof. Ping Tan.

Our work Model-driven Sketch Reconstruction with Structure-oriented Retrieval has been accepted by the ACM SIGGRAPH Asia 2016 Technical Briefs Program.

Attended SIGGRAPH Asia 2014 in Shenzhen for the first time.

Registration at HKUST. A whole new journey started.

Graduated from Shandong University.

A trip to Qingdao.

Graduation examination.

Early admission to CSE @ HKUST.

Onsite interview of CSE @ HKUST in Beijing.

Internship at Zhejiang University.