Taihang Hu
|
MS student [Google Scholar] [Github] [E-mail] |
About Me
I am currently a third-year MS student at Tianjin Key Laboratory of Visual Computing and Intelligent Perception (VCIP, the lab is lead by Ming-Ming Cheng), Nankai University, advised by Prof. Yaxing Wang. My research interests lie in Controllable image generation and editing that better aligns with human preferences, as well as a unified model for understanding and generation.
News
- [05/2026] Two papers about distillation of diffusion models(CDM) and optimization of training strategies((PAE)) have been released. We have achieved state-of-the-art results under the standard evaluation setting. Please stay tuned if you are interested!
- [05/2026] One paper was accepted by ICML 2026.
- [01/2026] One paper (ORION) was accepted by ICLR 2026.
- [06/2025] Two papers were accepted by ICCV 2025(including IsLock and MetaUnlearning)
- [10/2024] I get the NeurIPS 2024 Scholar Award, Looking forward to meeting in Vancouver ^_^
- [09/2024] Three papers were accepted by NeurIPS 2024 (including one spotlight).
- [01/2024] One paper was accepted by ICLR 2024.
- [08/2023] Started my MS journey at Nankai University.
- [06/2023] Happy to graduate from Chongqing University. Thank you to all my classmates and teachers!
- [05/2023] See our new work, StyleDiffusion for image editing
Publications
(* indicates equal contribution, # indicates Corresponding author)
-
What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion
Zhengrong Yue, Taihang Hu, Mengting Chen, Haiyu Zhang, Zihao Pan, Tao Liu, Zikang Wang, Jinsong Lan, Xiaoyong Zhu, Bo Zheng#, Yali Wang#
[Paper] -
Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
Tao Liu, Hao Yan, Mengting Chen, Taihang Hu, Zhengrong Yue, Zihao Pan, Jinsong Lan, Xiaoyong Zhu, Ming-Ming Cheng, Bo Zheng, Yaxing Wang
[Paper] -
ORION: Decoupling and Alignment for Unified Autoregressive Understanding and Generation
Taihang Hu, Mengting Chen, Jinsong Lan, Xiaoyong Zhu, Kaifu Zhang, Ming-Ming Cheng, Bo Zheng, Yaxing Wang (ICLR 2026)
[Paper] -
Anchor Token Matching: Implicit Structure Locking for Training-free AR Image Editing
Taihang Hu, Linxuan Li, Kai Wang, Yaxing Wang, Jian Yang, Ming-Ming Cheng(ICCV 2025)
[Paper] [Code] -
Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts
Hongcheng Gao*, Tianyu Pang*, Chao Du, Taihang Hu, Zhijie Deng, Min Lin(ICCV 2025)
[Paper] [Code] -
Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
Taihang Hu, Linxuan Li, Joost van de Weijer, Hongcheng Gao, Fahad Khan, Jian Yang, Ming-Ming Cheng, Kai Wang, Yaxing Wang(NeurIPS 2024)
[Paper] [Code]
-
Faster Diffusion: Rethinking the Role of UNet Encoder in Diffusion Models
Senmao Li*, Taihang Hu*, Fahad Shahbaz Khan, Linxuan Li, Shiqi Yang, Yaxing Wang#, Ming-Ming Cheng, Jian Yang(NeurIPS 2024, the order of the Co-first authors was determined by coin flip.)
[Paper] [Code]
-
Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning
Jiadong Pan*, Hongcheng Gao*, Zongyu Wu, Taihang Hu, Li Su, Liang Li, Qingming Huang(NeurIPS 2024 Spotlight )
-
Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models
Senmao Li, Joost van de Weijer, Taihang Hu, Fahad Shahbaz Khan, Qibin Hou, Yaxing Wang#, Jian Yang(ICLR 2024)
[Paper] [Code]
-
StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing
Senmao Li, Joost van de Weijer, Taihang Hu, Fahad Shahbaz Khan, Qibin Hou, Yaxing Wang#, Jian (CVMJ 2024)
[Paper] [Code]
Education
-
M.S. in Computer Science and Technology (Sep. 2023 - Present) Nankai University, Chongqing, China
-
B.E. in Computer Science and Technology (Sep. 2019 - Jun. 2023) Chongqing University, Chongqing, China
Honors & Award
Outstanding UG graduate, Outstanding student in Chongqing University, 2023
Advanced Individual in Enhancing Innovation Capabilities in Chongqing University, 2022
China Undergraduate Mathematical Contest in Modeling, National First Prize, 2021