Xiangyu Xu | OpenReview

Toggle navigationOpenReview.net

• Login

Names

Xiangyu Xu (Preferred), xiangyu xu

• Suggest Name

Emails

****@mails.tsinghua.edu.cn (Confirmed), ****@gmail.com (Confirmed)

• Suggest Email

Personal Links

HomepageGoogle ScholarDBLP

• Suggest URL

Career & Education History

Full ProfessorXi'an Jiaotong University (xjtu.edu.cn)2023 – Present ResearcherSea AI Lab (sea.com)2021 – 2023 PostdocCarnegie Mellon University (cmu.edu)2019 – 2020 PhD studentTsinghua University (tsinghua.edu.cn)2013 – 2018 Undergrad studentTsinghua University (tsinghua.edu.cn)2009 – 2013 

• Suggest Position

Advisors, Relations & Conflicts

PhD AdvisorMing-Hsuan Yang2015 – 2018 PhD AdvisorYu-Jin Zhang2013 – 2018 

• Suggest Relation

Expertise

Embodied AI2024 – Present 3D Computer Vision2019 – Present 3D Human Reconstruction2019 – Present Generative AI2015 – Present 

• Suggest Expertise

Publications

• Boolean Satisfiability via Imitation Learning

  Zewei Zhang, Huan Liu, YUANHAO YU, Jun Chen, Xiangyu Xu
  • ICLR 2026 Poster
  • Readers: Everyone

• Robust Neural Rendering in the Wild with Asymmetric Dual 3D Gaussian Splatting

  Chengqi Li, Zhihao Shi, Yangdi Lu, Wenbo He, Xiangyu Xu
  • NeurIPS 2025 spotlight
  • Readers: Everyone

• WMarkGPT: Watermarked Image Understanding via Multimodal Large Language Models

  Songbai Tan, Xuerui Qiu, Yao Shu, Gang Xu, Linrui Xu, Xiangyu Xu, Huiping Zhuang, Ming Li, Fei Yu
  • ICML 2025 poster
  • Readers: Everyone

• Instant3D: Instant Text-to-3D Generation

  Ming Li, Pan Zhou, Jia-Wei Liu, Jussi Keppo, Min Lin, Shuicheng Yan, Xiangyu Xu
  • Int. J. Comput. Vis. 2024
  • Readers: Everyone

• Progressive Multi-scale Triplane Network for Text-to-3D Generation

  Han Yi, Zhedong Zheng, Xiangyu Xu, Tat-Seng Chua
  • Submitted to ICLR 2025
  • Readers: Everyone

• GoodDrag: Towards Good Practices for Drag Editing with Diffusion Models

  Zewei Zhang, Huan Liu, Jun Chen, Xiangyu Xu
  • ICLR 2025 Poster
  • Readers: Everyone

• Towards Garment Sewing Pattern Reconstruction from a Single Image

  Xiangyu Xu
  • OpenReview Archive Direct Upload
  • Readers: Everyone

• NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF

  Xiangyu Xu
  • OpenReview Archive Direct Upload
  • Readers: Everyone

• Instant3D: Instant Text-to-3D Generation

  Xiangyu Xu
  • OpenReview Archive Direct Upload
  • Readers: Everyone

• SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimation

  Xiangyu Xu
  • OpenReview Archive Direct Upload
  • Readers: Everyone

View all 37 publications

Co-Authors

• Bolei Zhou
• Chen Change Loy
• Chengqi Li
• Chenyang Liu
• Fei Yu
• Fernando De la Torre
• Francesc Moreno-Noguer
• Gang Xu
• Gim Hee Lee
• Han Yi
• Hao Chen
• Hehe Fan
• Huan Liu
• Huiping Zhuang
• Jia-Wei Liu
• Jiabin Liang
• Jiahe Li
• Jianfeng Zhang
• Jiashi Feng
• Jinwei Gu
• Jun Chen
• Jun Liu
• Jussi Keppo
• Kai Chen
• Kelvin C.K. Chan

View all 55 co-authors

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2026 OpenReview