Prof. Peng Hu

Peng Hu (胡鹏) is currently a professor at the College of Computer Science, Sichuan University. From 2019 to 2020, he was a research scientist at Institute for Infocomm, Research Agency for Science, Technology, and Research (A*STAR) Singapore. He received his Ph.D. degree in computer science and technology from Sichuan University, China, in 2019. His current interests mainly focus on multi-view learning, cross-modal retrieval, and network compression.

Published in , 1900

2026

• Changhao He, Di Xue, Shuxian Li, Yanji Hao, Xi Peng, Peng Hu#, Bootstrapping Multi-view Learning for Test-time Noisy Correspondence, The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
• Yiwen Shan, Haiyu Zhao, Peng Hu, Xi Peng, Yuanbiao Gou, Next-Scale Prediction: A Self-Supervised Approach for Real-World Image Denoising, The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
• Haochen Zhou, Guofeng Ding, Mouxing Yang, Peng Hu, Yijie Lin, Xi Peng, Uncover Underlying Correspondence for Robust Multi-view Clustering, The Fourteenth International Conference on Learning Representations (ICLR), 2026. (Oral, acc rate=1.18%)
• Haobin Li, Yijie Lin, Peng Hu, Mouxing Yang, Xi Peng, Learning with Dual-level Noisy Correspondence for Multi-modal Entity Alignment, The Fourteenth International Conference on Learning Representations (ICLR), 2026. (Oral, acc rate=1.18%)
• Yang Qin, Yuan Sun, Xi Peng, Dezhong Peng, Joey Tianyi Zhou, Xiaomin Song, Peng Hu#, Robust Semi-paired Multimodal Learning for Cross-modal Retrieval, The Fortieth AAAI Conference on Artificial Intelligence (AAAI 2026), Jan. 20-27, Singapore, 2026.
• Haobin Li, Yijie Lin, Peng Hu, Mouxing Yang#, Xi Peng#, Community-aware Multi-view Representation Learning with Incomplete Information, IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), 2026.

Research Interests

• Multimodal Learning
• Multimedia Analysis
• Neural Network Compression