Xu Han
Multimodality & Generation
Master’s degree in Computer Science · HUST
Make it count.
Biography
Background
I recently completed a master’s degree in computer science at Huazhong University of Science and Technology, where I was advised by Prof. Xianzhi Li. I was a research intern at King Abdullah University of Science and Technology (KAUST), working with Prof. Peter Wonka. Before that, I received my B.Eng. degree with honors from the School of Computer Science at Shandong University in 2023, where I worked closely with Prof. Mengbai Xiao.
Research interests
My research focuses on multimodal learning and generative modeling. I am especially interested in structured, simple, and scalable approaches to learning from diverse multimodal data and generating coherent content across modalities.
I welcome academic collaborations in these directions.
Research outlook
Going forward, I hope to develop models that can learn, reason, and generate across modalities, guided by structure rather than unnecessary complexity.
Publications
Generative Models · Multimodal Learning · 3D Vision * equal contribution · † corresponding author
PointDreamer: Zero-Shot 3D Textured Mesh Reconstruction From Colored Point Cloud
MoST: Efficient Monarch Sparse Tuning for 3D Representation Learning
Fancy123: One Image to High-Quality 3D Mesh Generation via Plug-and-Play Deformation
SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds
More Text, Less Point: Towards 3D Data-Efficient Point-Language Understanding
Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model
MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors
patchDPCC: A Patchwise Deep Compression Framework for Dynamic Point Clouds
Academic service
ReviewerCVPR · ACM Multimedia · AAAI