Hu Yu

I am a forth-year PhD student at University of Science and Technology of China, advised by Feng Zhao.

My research interest lies in diffusion model, autoregressive model, unified understanding and generation model, and world model. Any discussions and cooperations are warmly welcomed!

Email / Google Scholar

News

1 paper accepted to CVPR 2025 as Highlight
2 paper accepted to ECCV 2024
1 paper accepted to ACM MM 2024
1 paper accepted to WACV 2024
1 paper accepted to NeurIPS 2023 as Spotlight
2 paper accepted to CVPR 2023
1 paper accepted to NeurIPS 2022 as Featured paper
2 paper accepted to ACM MM 2022
2 paper accepted to ECCV 2022

Research

In the last year, my research mainly lies in autoregressive image & video generation, and unified understanding & generation model. For full list of my publications, please refer to my Google Scholar for full publications.

	VideoMAR: Autoregressive Video Generation with Continuous Tokens Hu Yu, Biao Gong, Hangjie Yuan, DanDan Zheng, Weilong Chai, Jingdong Chen, Kecheng Zheng, Feng Zhao Arxiv paper / project page
	Frequency Autoregressive Image Generation with Continuous Tokens Hu Yu, Hao Luo, HangJie Yuan, Yu Rong, Feng Zhao Arxiv paper / project page
	DualFast: Dual-Speedup Framework for Fast Sampling of Diffusion Models Hu Yu, Hao Luo, Fan Wang, Feng Zhao Arxiv paper /
	Uncovering the Text Embedding in Text-to-Image Diffusion Models Hu Yu, Hao Luo, Fan Wang, Feng Zhao Arxiv paper / project page
	Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction Biao Gong, Cheng Zou, Dandan Zheng, Hu Yu, Jingdong Chen, Jianxin Sun, Junbo Zhao, Jun Zhou, Kaixiang Ji, Lixiang Ru, Libin Wang, Qingpei Guo, Rui Liu, Weilong Chai, Xinyu Xiao, Ziyuan Huang Arxiv paper / code
	High-quality Image Dehazing with Diffusion Model Hu Yu, Jie Huang, Kaiwen Zheng, Man Zhou, Feng Zhao. Arxiv paper / code
	FreePCA: Integrating Consistency Information across Long-short Frames in Training-free Long Video Generation via Principal Component Analysis Jiangtong Tan, Hu Yu, Jie Huang, Jie Xiao, Feng Zhao CVPR, 2025 Spotlight paper / code
	Unmasking Bias in Diffusion Model Training Hu Yu, Li Shen, Jie Huang, Hongsheng Li, Feng Zhao ECCV, 2024 paper / code
	Unleashing the Potential of the Semantic Latent Space in Diffusion Models for Image Dehazing Zizheng Yang, Hu Yu, Bing Li, Jinghao Zhang, Jie Huang, Feng Zhao ECCV, 2024 paper /
	FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining Zhen Zou, Hu Yu, Zhao Feng ACM MM, 2024 paper / code
	Deep Fractional Fourier Transform Hu Yu, Jie Huang, Lingzhi Li, Man Zhou, Feng Zhao. NeurIPS, 2023 Highlight paper / code
	Visual Recognition-driven Image Restoration for Multiple Degradation with Intrinsic Semantics Recovery Zizheng Yang, Jie Huang, Jiahao Chang, Man Zhou, Hu Yu, Jinghao Zhang, Feng Zhao CVPR, 2023 paper
	Ingredient-oriented Multi-degradation Learning for Image Restoration Jinghao Zhang, Jie Huang, Mingde Yao, Zizheng Yang, Hu Yu, Man Zhou, Feng Zhao CVPR, 2023 paper / code
	Deep Fourier Up-Sampling Man Zhou, Hu Yu, Jie Huang, Feng Zhao, Jinwei Gu, Chen Change Loy, Deyu Meng, Chongyi Li NeurIPS, 2022 Featured paper paper / code
	Source-Free Domain Adaptation for Real-world Image Dehazing Hu Yu, Jie Huang, Yajing Liu, Qi Zhu, Man Zhou, Feng Zhao ACM MM, 2022 paper
	Adaptively Learning Low-high Frequency Information Integration for Pan-sharpening Man Zhou, Jie Huang, Chongyi Li, Hu Yu, Keyu Yan, Naishan Zheng, Feng Zhao ACM MM, 2022 paper
	Spatial-Frequency Domain Information Integration for Pan-sharpening Man Zhou, Jie Huang, Keyu Yan, Hu Yu, Xueyang Fu, Aiping Liu, Xian Wei, Feng Zhao ECCV, 2022 paper
	Frequency and Spatial Dual Guidance for Image Dehazing Hu Yu, Naishan Zheng, Man Zhou, Jie Huang, Zeyu Xiao, Feng Zhao ECCV, 2022 paper / code

Awards

National Scholarship
National Encouragement Scholarship
First-class Academic Scholarship

Service

Reviewer of NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, ACM MM, AAAI

Stolen from Jon Barron