Tang,Hao
Personal Homepage: https://ha0tang.github.io/
Hao Tang, Ph.D., serves as Assistant Professor and Researcher, Doctoral Supervisor, Boya Young Scholar, and Weiming Young Scholar at the School of Computer Science, Peking University. He is also the Director of the Embodied and Generative AI Laboratory of Peking University and a research supervisor for the Turing Class of Peking University. He has been selected for the national high-level overseas talent program and awarded the National Excellent Overseas Student Award (Returning Scholar Category). Additionally, he has been listed in Stanford University’s World's Top 2% Scientists Ranking for three consecutive years from 2023 to 2025. He completed his postdoctoral research at Carnegie Mellon University (CMU) in the United States and ETH Zurich in Switzerland, and earned his doctoral degree from the University of Trento, Italy. He has also conducted academic visits and research internships at prestigious institutions including the University of Oxford, National University of Singapore, Northeastern University (USA), and the IIAI in the UAE. Beyond academic research, he actively promotes industry-university-research integration and has served as a senior technical advisor for multiple startups across the United States, the United Kingdom, Romania and China.
Selected Publications
Hao Tang has published over 100 papers in top-tier international journals and conferences, including CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, AAAI, IJCAI, ACM MM, ICRA, IROS, CoRL, ACL, NAACL, 3DV, AAMAS, TPAMI, IJCV and TVCG. His research works have accumulated more than 13,000 citations from peers worldwide (as of April 2026). He has also received numerous international academic honors, among which includes the Best Paper Honorable Mention at ACM MM 2018, with only 4 out of 757 papers shortlisted for the nomination.
Selected Publications (*Corresponding Author(s))
[1] Jiawei Mao, Yu Yang, Xuesong Yin, Ling Shao, Hao Tang*. AllRestorer: All-in-One Transformer for Image Restoration under Composite Degradations. IEEE TPAMI, 2026
[2] Hao Tang, Ling Shao, Zhenyu Zhang, Luc Van Gool, Nicu Sebe. Spatial-Temporal Graph Mamba for Music-Guided Dance Video Synthesis. IEEE TPAMI, 2025
[3] Hao Tang, Ling Shao, Nicu Sebe, Luc Van Gool. Enhanced Multi-Scale Cross-Attention for Person Image Generation. IEEE TPAMI, 2025
[4] Hao Tang, Ling Shao, Nicu Sebe, Luc Van Gool. Graph Transformer GANs with Graph Masked Modeling for Architectural Layout Generation. IEEE TPAMI, 2024
[5] Hui Wei, Hao Tang, Xuemei Jia, Zhixiang Wang, Hanxun Yu, Zhubo Li, Shin'ichi Satoh, Luc Van Gool, Zheng Wang. Physical Adversarial Attack Neets Computer Vision: A Decade Survey. IEEE TPAMI, 2024
[6] Hao Tang, Guolei Sun, Nicu Sebe, Luc Van Gool. Edge Guided GANs with Multi-Scale Contrastive Learning for Semantic Image Synthesis. IEEE TPAMI, 2023
[7] Hao Tang, Philip HS Torr, Nicu Sebe. Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation. IEEE TPAMI, 2022
[8] Hao Tang, Ling Shao, Philip HS Torr, Nicu Sebe. Local and Global GANs with Semantic-Aware Upsampling for Image Generation. IEEE TPAMI, 2022
[9] Songtao Li, Hao Tang*. Multimodal Alignment and Fusion: A Survey. Springer IJCV, 2025
[10] Hao Tang, Ling Shao, Philip HS Torr, Nicu Sebe. Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis. Springer IJCV, 2022
[11] Hongpeng Wang, Zeyu Zhang, Wenhao Li, Hao Tang*. MoRL: Reinforced Reasoning for Unified Motion Understanding and Generation. In ACL 2026, San Diego, USA
[12] Yuxuan Fan, Jing Hao, Hong Chen, Jiahao Bao, Yihua Shao, Yuci Liang, Kuo Feng Hung, Hao Tang*. OralGPT-Plus: Learning to Use Visual Tools via Reinforcement Learning for Panoramic X-ray Analysis. In CVPR 2026, Denver, USA
[13] Jun Liu, Zhenglun Kong, Peiyan Dong, Changdi Yang, Tianqi Li, Hao Tang*, et al. Structured Agent Distillation for Large Language Model Agents. In AAMAS 2026, Paphos, Cyprus
[14] Zhengri Wu, Yiran Wang, Yu Wen, Zeyu Zhang, Biao Wu, Hao Tang*. StereoAdapter: Adapting Stereo Depth Estimation to Underwater Scenes. In ICRA, 2026, Vienna, Austria
[15] Nonghai Zhang, Zeyu Zhang, Jiazi Wang, Yang Zhao, Hao Tang*. VaseVQA-3D: Benchmarking 3D VLMs on Ancient Greek Pottery. In ICLR, 2026, Rio de Janeiro, Brazil
[16] Ting Huang, Zeyu Zhang, Yemin Wang, Hao Tang*. 3D Coca: Contrastive Learners Are 3D Captioners. In 3DV 2026, Vancouver, Canada
[17] Fanhu Zeng, Haiyang Guo, Fei Zhu*, Li Shen, Hao Tang*. RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness. In NeurIPS 2025, San Diego, USA
[18] Qinhua Xie, Hao Tang*. TTTFusion: A Test-Time Training-Based Strategy for Multimodal Medical Image Fusion in Surgical Robots. In IROS 2025, Hangzhou, China
[19] Xiaoyi Liu, Hao Tang*. DiffFNO: Diffusion Fourier Neural Operator. In CVPR 2025, Nashville, USA
[20] Renkai Wu, Xianjin Wang, Pengchen Liang, Zhenyu Zhang, Qing Chang*, Hao Tang*. Toward Zero-Shot Learning for Visual Dehazing of Urological Surgical Robots. In ICRA 2025, Atlanta, USA
