CV

Education

Ph.D. in Computer Science and Engineering, The Chinese University of Hong Kong, 2026 - present
M.S. in Computer Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, 2023 - 2026
B.S. in Physics, University of Chinese Academy of Sciences, 2018 - 2022

Research experience

2025 - present: Ph.D. Student
- The Chinese University of Hong Kong
- Research area: multimodal learning, robotics
- Supervisor: Prof. Your Advisor
2024 - 2025: Research Intern / Undergraduate Research Assistant
- Your University
- Duties included: Literature review, experiments, and paper writing
- Supervisor: Prof. Your Advisor

Skills

Programming: Python, PyTorch
Research: generative models, diffusion models, robotics, deep learning
Languages: Mandarin (native), English (fluent)

Publications

Reinforcement Learning-driven Diffusion Models: Language, Vision, and Beyond

Zhiyuan Ma, Jiabao Wei, Tianyu Wang, Hanqing Wang, Jiadong Pan, Haowen Xu, Liangliang Zhao, Ruixun Liu, Yuhan Wang, Yuwei Zhang, Liang Feng, Junhao Xiao, Kaiyan Zhang, Xuekai Zhu, Daizong Liu, Biqing Qi, Yihao Liu, Ganqu Cui, Ning Ding, Linfeng Zhang, Jianjun Li, Kun He, Xiang Bai, Bowen Zhou. (2026). "Reinforcement Learning-driven Diffusion Models: Language, Vision, and Beyond." IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models

Jiadong Pan, Liang Li, Yuxin Peng, Yu-Ming Tang, Shuohuan Wang, Yu Sun, Hua Wu, Qingming Huang, Haifeng Wang. (2026). "Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

SafeCFG: Controlling Harmful Features with Dynamic Safe Guidance for Safe Generation

Jiadong Pan, Liang Li, Hongcheng Gao, Zheng-Jun Zha, Qingming Huang, Jiebo Luo. (2025). "SafeCFG: Controlling Harmful Features with Dynamic Safe Guidance for Safe Generation." ACM International Conference on Multimedia (ACM MM).

FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing

Gaoxiang Cong*, Liang Li*, Jiadong Pan*, Zhedong Zhang, Amin Beheshti, Anton van den Hengel, Yuankai Qi, Qingming Huang (* Equal contribution). (2025). "FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing." ACM International Conference on Multimedia (ACM MM).

Semantic Energy: Detecting LLM Hallucination Beyond Entropy

Huan Ma, Jiadong Pan, Jing Liu, Yan Chen, Joey Tianyi Zhou, Guangyu Wang, Qinghua Hu, Hua Wu, Changqing Zhang, Haifeng Wang. (2025). "Semantic Energy: Detecting LLM Hallucination Beyond Entropy." arXiv preprint arXiv:2508.14496.

EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing

Gaoxiang Cong*, Jiadong Pan*, Liang Li, Yuankai Qi, Yuxin Peng, Anton van den Hengel, Jian Yang, Qingming Huang (* Equal contribution). (2025). "EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing." IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (Highlight).

Self-Reflective Reinforcement Learning for Diffusion-Based Image Reasoning Generation

Jiadong Pan, Zhiyuan Ma, Kaiyan Zhang, Ning Ding, Bowen Zhou. (2025). "Self-Reflective Reinforcement Learning for Diffusion-Based Image Reasoning Generation." arXiv preprint arXiv:2505.22407.

Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning

Jiadong Pan, Hongcheng Gao, Zongyu Wu, Taihang Hu, Li Su, Qingming Huang, Liang Li. (2024). "Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning." Conference on Neural Information Processing Systems (NeurIPS) (Spotlight).

Teaching

Teaching Assistant: Data Structures and Algorithms

Teaching Assistant: Introduction to Machine Learning

Service and leadership

Reviewer for NeurIPS (2025, 2026), ICLR (2025, 2026), CVPR 2026, ECCV 2026, CoRL 2026, IEEE TPAMI

Jiadong Pan

CV