Fan Zhang (章帆)

Ph.D. Student

Department of Computer Science and Engineering

The Chinese University of Hong Kong

Email: fzhang25 [at] cse (dot) cuhk (dot) edu (dot) hk

WeChat: ZF_Karl

Google Scholar / GitHub / Email / WeChat

I am a second-year Ph.D. student at the Department of Computer Science and Engineering (CSE), The Chinese University of Hong Kong (CUHK), supervised by Prof. Pheng-Ann Heng. Previously, I have spent wonderful times as a research intern at Tencent YouTu Lab, Alibaba Qwen Team, Tencent LightSpeed Studios (Project Up 青云计划), and Inclusion AI, Ant Group (Plan A 蚂蚁星计划).

My research interests lie at the intersection of Large Language Models (LLMs), Multimodal Understanding, and Agentic Systems. My long-term goal is to build intelligent systems that perceive the real world, reason about it, and act on their own decisions.

I am always open to communication and collaboration. Please feel free to get in touch.

News

[05/2026] Two papers are accepted by ICML 2026. Congrats to all!
[01/2026] Two papers are accepted by ICLR 2026. Congrats to all!
[11/2025] Two papers are accepted by AAAI 2026. Congrats to all!
[09/2025] One paper is accepted by NeurIPS 2025 Datasets and Benchmarks Track.
[08/2025] I join CUHK CSE Department as a Ph.D. student, under the supervision of Prof. Pheng-Ann Heng.
[04/2025] I start my internship at Qwen-Audio Team, Alibaba Group.
[08/2024] I start my internship at YouTu Lab, Tencent.

Selected Publications (Full Publications)

My name is shown in bold, * denotes equal contribution and † denotes corresponding author.

DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment

Xinyu Geng*, Xuanhua He*, Sixiang Chen*, Yanjing Xiao, Fan Zhang, Shijue Huang, Haitao Mi, Zhenwen Liang†, Tianqing Fang†, Yi R. Fung†

Association for Computational Linguistics: EMNLP, 2026 [Paper] [Code] [Data]

Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking

Fan Zhang*, Vireo Zhang*, Shengju Qian†, Haoxuan Li, Zheng Lian, Hao Wu, Yuan Gao, Xinyu Geng, Xin Wang, Pheng-Ann Heng

Conference on Language Modeling (COLM), 2026 [Paper]

Learning to Memorize with Attributive and Associative Memory for Online Test-Time Adaptation of Vision-Language Models

Yuchao Zhang, Hao Wang, Fan Zhang, Qirui Mi, Mengyue Yang, Yisen Wang, Jun Wang, Haoxuan Li, Zhouchen Lin

International Conference on Machine Learning (ICML), 2026 [Paper]

MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models

Fan Zhang*, Zebang Cheng*, Chong Deng*, Haoxuan Li, Zheng Lian, Qian Chen, Huadai Liu, Wen Wang, YiFan Zhang, Renrui Zhang, Ziyu Guo, Zhihong Zhu, Hao Wu, Haixin Wang, Yefeng Zheng, Xiaojiang Peng†, Xian Wu, Kun Wang†, Xiangang Li, Jieping Ye, Pheng-Ann Heng†

International Conference on Learning Representations (ICLR), 2026 [Paper] [Project] [Code] [Data]

EmoPrefer: Can Large Language Models Understand Human Emotion Preferences?

Zheng Lian, Licai Sun, Lan Chen, Haoyu Chen, Zebang Cheng, Fan Zhang, Ziyu Jia, Ziyang Ma, Fei Ma, Xiaojiang Peng, Jianhua Tao

International Conference on Learning Representations (ICLR), 2026 [Paper] [Code]

CellVerse: Do Large Language Models Really Understand Cell Biology?

Fan Zhang, Tianyu Liu, Zhihong Zhu, Hao Wu, Haixin Wang, Donghao Zhou, Yefeng Zheng, Kun Wang†, Xian Wu†, Pheng-Ann Heng†

Conference on Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track, 2025 [Paper] [Code]

DREAM: Decoupled Discriminative Learning with Bigraph-aware Alignment for Semi-supervised 2D-3D Cross-modal Retrieval

Fan Zhang, Changhu Wang, Zebang Cheng, Xiaojiang Peng, Dongjie Wang, Yijia Xiao, Chong Chen, Xian-Sheng Hua, Xiao Luo†

Annual AAAI Conference on Artificial Intelligence (AAAI), 2025 [Paper]

Semi-supervised Knowledge Transfer Across Multi-omic Single-cell Data

Fan Zhang, Tianyu Liu, Zihao Chen, Xiaojiang Peng, Chong Chen, Xian-Sheng Hua, Xiao Luo†, Hongyu Zhao

Conference on Neural Information Processing Systems (NeurIPS), 2024 [Paper] [Code]

Fine-grained Prototypical Voting with Heterogeneous Mixup for Semi-supervised 2D-3D Cross-modal Retrieval

Fan Zhang, Xian-Sheng Hua, Chong Chen, Xiao Luo†

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 [Paper]

DEMO: A Statistical Perspective for Efficient Image-Text Matching

Fan Zhang, Xian-Sheng Hua, Chong Chen, Xiao Luo†

North American Chapter of the Association for Computational Linguistics (NAACL), 2024 [Paper] [Code]

HOPE: A Hierarchical Perspective for Semi-supervised 2D-3D Cross-Modal Retrieval

Fan Zhang, Hang Zhou, Xian-Sheng Hua, Chong Chen, Xiao Luo

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024 [Paper] [Code]

FATE: Learning Effective Binary Descriptors with Group Fairness

Fan Zhang, Chong Chen, Xian-Sheng Hua, Xiao Luo

IEEE Transactions on Image Processing (TIP), 2024 [Paper]

Preprints

Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding

Hongyu Qu*, Guangming Yao*, Ling Xing, Xiaobin Hu, Rongxing Ding, Guibin Zhang, Fan Zhang, Yi Yuan, Xiangbo Shu†, Shuicheng Yan

arXiv preprint, 2026 [Paper]

VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understanding

Fan Zhang*, Guangming Yao*, Jinyang Wu, Hao Wu, Zheng Lian, Xinyu Geng, Jingdong Chen, Yi Yuan†, Pheng-Ann Heng†

arXiv preprint, 2026 [Paper] [Code] [Data]

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Jinyang Wu*†, Shuo Yang*, Zhengxi Lu, Fan Zhang, Yuhao Shen, Lang Feng, Haoran Luo, Zheng Lian, Shuai Zhang, Zhengqi Wen, Jianhua Tao

arXiv preprint, 2026 [Paper] [Code]

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

Shuo Yang*, Jinyang Wu*†, Zhengxi Lu, Yuhao Shen, Fan Zhang, Lang Feng, Shuai Zhang, Haoran Luo, Zheng Lian, Zhengqi Wen, Jianhua Tao

arXiv preprint, 2026 [Paper] [Code]

Orchestra-o1: Omnimodal Agent Orchestration

Fan Zhang*, Vireo Zhang*, Shengju Qian†, Haoxuan Li, Hao Wu, Jinyang Wu, Donghao Zhou, Zhihong Zhu, Zheng Lian, Xin Wang, Pheng-Ann Heng†

arXiv preprint, 2026 [Paper] [Code] [Model]

OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics

Mingxian Lin, Shengju Qian, Yuqi Liu, Yi-Hua Huang, Yiyu Wang, Wei Huang, Yitang Li, Fan Zhang, Zeyu Hu, Lingting Zhu, Xin Wang, Xiaojuan Qi†

arXiv preprint, 2026 [Paper] [Project] [Code]

Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles

Jinyang Wu*, Guocheng Zhai*, Ruihan Jin*, Yuhao Shen, Zhengxi Lu, Fan Zhang, Haoran Luo, Zheng Lian†, Zhengqi Wen†, Jianhua Tao

arXiv preprint, 2026 [Paper]

AffectGPT-RL: Revealing Roles of Reinforcement Learning in Open-Vocabulary Emotion Recognition

Zheng Lian, Fan Zhang, Lan Chen, Yazhou Zhang, Rui Liu, Jinyang Wu, Haoyu Chen, Xiaobai Li, Xiaojiang Peng, Bin He, Jianhua Tao

arXiv preprint, 2026 [Paper]

Rethinking Facial Expression Recognition in the Era of Multimodal Large Language Models: Benchmark, Datasets, and Beyond

Fan Zhang, Haoxuan Li, Shengju Qian†, Xin Wang, Zheng Lian, Hao Wu, Zhihong Zhu, Yuan Gao, Qiankun Li, Yefeng Zheng, Zhouchen Lin†, Pheng-Ann Heng

arXiv preprint, 2025 [Paper] [Code] [Data]

Teaching

Teaching Assistant, The Chinese University of Hong Kong

ENGG1110D Problem Solving By Programming, Fall 2025
CSCI2100A Data Structure, Spring 2026
CSCI1550 Computer Principles and Python Programming, Fall 2026

Professional Activities

Conference Reviewer: ICML, ICLR, NeurIPS, CVPR, ICCV, KDD, AAAI, CIKM, ACM MM, ACL ARR
Journal Reviewer: IEEE TKDE, IEEE TNNLS, IEEE TAFFC, IEEE TCSVT, IEEE TMM, PLOS ONE
Program Chair: AAAI 2026 Bridge: Logical and Symbolic Reasoning in Language Models