I am a second-year Ph.D. student at Department of Computer Science and Engineering (CSE), The Chinese University of Hong Kong (CUHK) , supervised by Prof. Pheng-Ann Heng and Prof. Chi-Wing Fu, Philip. I have spent wonderful time at Tencent YouTu Lab, Zhejiang Lab, and Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences as a research intern/assistant. Also, it is my great honor to be awarded a China Postgraduate National Scholarship and a China Undergraduate National Scholarship during my academic career.

My research interest mainly includes Deep Learning and Computer Vision. Recently, I focus on exploring Generative AI, Multi-Modal Learning, and AI Agents, aiming to promote the efficiency and flexibility of AI models and algorithms in the real world.

📢📢📢 If you would like to discuss potential opportunities for collaboration, please feel free to contact me. 😊

🔥 News

  • 2025.11IdentityStory is accepted by AAAI 2025! 🎉
  • 2025.09SceneDecorator, BlindFormer, and CellVerse are accepted by NeurIPS 2025! 🎉
  • 2025.08OmniMol is accepted by Nature Communications! 🎉
  • 2025.06TRIG is accepted by ICCV 2025! 🎉
  • 2025.05MoIE is early accepted by MICCAI 2025 as a spotlight! 🎉
  • 2025.04MagicTailor is accepted by IJCAI 2025 as an oral! 🎉
  • 2024.12MM-Mixing is accepted by AAAI 2025! 🎉
  • 2024.10Dual-Schedule Inversion is accepted by WACV 2025 as an oral! 🎉
  • 2024.07DISCO and SignVTCL are accepted by BMVC 2024! 🎉
  • 2024.06IFAST is accepted by IEEE TIFS 2024 (a CCF-A journal)! 🎉
  • 2024.05   I am selected as an outstanding graduate of Beijing! 👨‍🎓
  • 2023.10DDPMask is accepted by WACV 2024! 🎉
  • 2023.10   I am awarded a China Postgraduate National Scholarship! 🏆
  • 2023.04   I join Tencent YouTu Lab as a research intern! 🔬
  • 2023.03RepMode is selected as a CVPR Highlight (Top 2.6% of 9155 submissions)! 🎉
  • 2023.02RepMode is accepted by CVPR 2023! 🎉
  • 2022.07   I join Zhejiang Lab as a research intern! 🔬
  • 2022.07EM Loss+APL is accepted by ECCV 2022! 🎉
  • 2021.03   I join SIAT, CAS as a research assistant! 🔬
  • 2020.09   I am awarded a China Undergraduate National Scholarship! 🏆

📝 Selected Publications

(* Equal Contribution, Project Lead)

NeurIPS 2025
sym

SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency

Quanjian Song*, Donghao Zhou*, Jingyu Lin*, Fei Shen, Jiaze Wang, Xiaowei Hu, Cunjian Chen,

Pheng-Ann Heng

Annual Conference on Neural Information Processing Systems (NeurIPS) 2025

[Page] [Paper] [Code]


Nat. Commun.
sym

Unified and Explainable Molecular Representation Learning for Imperfectly Annotated Data from the Hypergraph View

Bowen Wang, Junyou Li, Donghao Zhou, Lanqing Li, Jinpeng Li, Ercheng Wang, Jianye Hao, Liang Shi, Chengqiang Lu, Jiezhong Qiu, Tingjun Hou, Dongsheng Cao, Guangyong Chen, Pheng-Ann Heng

Nature Communications

[Paper] [Code]


IJCAI 2025 Oral
sym

MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models

Donghao Zhou*, Jiancheng Huang*, Jinbin Bai, Jiaze Wang, Hao Chen, Guangyong Chen,

Xiaowei Hu, Pheng-Ann Heng

International Joint Conference on Artificial Intelligence (IJCAI) 2025 Oral

[Page] [Paper] [Code] [Poster]


IEEE TIFS
sym

IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Images

Jiancheng Huang*, Donghao Zhou*, Jianzhuang Liu, Linxiao Shi, Shifeng Chen

IEEE Transactions on Information Forensics and Security (TIFS) 2024 (CCF-A Journal)

[Page] [Paper] [Code]


BMVC 2024
sym

DISCO: Distribution-Aware Calibration for Object Detection with Noisy Bounding Boxes

Donghao Zhou, Jialin Li, Jinpeng Li, Jiancheng Huang, Qiang Nie, Yong Liu, Bin-Bin Gao,

Qiong Wang, Pheng-Ann Heng, Guangyong Chen

British Machine Vision Conference (BMVC) 2024

[Paper] [Code] [Poster]


CVPR 2023 Highlight
sym

RepMode: Learning to Re-parameterize Diverse Experts for Subcellular Structure Prediction

Donghao Zhou, Chunbin Gu, Junde Xu, Furui Liu, Qiong Wang, Guangyong Chen, Pheng-Ann Heng

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023 Highlight

[Page] [Paper] [Code] [Poster] [Talk]

Selected as a Highlight presentation paper (Top 2.6% of 9155 submissions)


ECCV 2022
sym

Acknowledging the Unknown for Multi-Label Learning with Single Positive Labels

Donghao Zhou, Pengfei Chen, Qiong Wang, Guangyong Chen, Pheng-Ann Heng

European Conference on Computer Vision (ECCV) 2022

[Paper] [Code] [Poster] [Slides]

👨‍💻 Experience

sym

Tencent YouTu Lab, Shenzhen, China

Research Intern @ FuXi Research Center

2023.04 - 2023.09


sym

Zhejiang Lab, Hangzhou, China

Research Intern @ Research Institute of Intelligent Computing

2022.07 - 2023.01


sym

Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China

Research Assistant @ CV2R-Lab

2021.03 - 2021.08

🏅 Selected Awards

  • 2024.05   Outstanding Graduate of Beijing & UCAS
  • 2024.02   SIAT President’s Special Scholarship
  • 2024.01   IAIT Dean’s Innovation Award: Outstanding Postgraduate Award
  • 2023.10   China Postgraduate National Scholarship (Top 1.7%)
  • 2021.04   Top 10 Student Innovation Figure (Bonus: 10,000 CNY)
  • 2020.09   China Undergraduate National Scholarship (Top 0.3%)
  • 2018 - 2020   First-Class Excellent Student Scholarships (Three Times)
  • 2019.05Asia-Pacific Robot Contest (ROBOCON), China Regional Competition, Second Prize (Leading a team of 30+ members)

📅 Academic Services

📖 Reviewers/PC Members

  • Conference: CVPR 2026, ICLR 2026, AAAI 2026, BMVC 2025, ICCV 2025, ICML 2025, AISTATS 2025, WACV 2025, AAAI 2025, NeurIPS 2024, BMVC 2024, ACCV 2024, ECCV 2024, CVPR 2024, ICCV 2023
  • Journal: Scientific Reports

🗣️ Teaching

  • 2025 - 2026Fall   Computer Principles and Python Programming (CSCI1550)
  • 2024 - 2025Spring   Introduction to Computing using Python (AIST1110)

💬 Invited Talks

  • 2023.06   Subcellular Structure Prediction: Revealing Fluorescent Images with Deep Learning, Topic Talk, held by TechBeat | [News] [Video]
  • 2022.12   Single Positive Multi-Label Learning, Youth Ph.D. Talk, held by ITIC and AI TIME | [News]