Multimodal Intelligence · Affective Computing

Zebang Cheng (程泽浜)

Ph.D. Student in Computer Science · Shenzhen University & Guangming Laboratory

I am a jointly trained Ph.D. student at Shenzhen University and Guangming Laboratory (Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)).

I have published more than 20 research papers, including work on audio-visual emotion understanding, reasoning, benchmarking, and multimodal agents.

Advisors: Prof. Laizhong Cui and Dr. Fei Ma.

Research interests: Multimodal Large Language Models, Affective Computing, Multimodal Emotion Understanding and Reasoning, Multimodal Agents.

Email: zebang.cheng AT gmail DOT com

Portrait of Zebang Cheng

News

  • We introduce SAGE, a multimodal agent system developed for the EgoLink 2026 Challenge.
  • Our teams took 1st, 2nd, and 3rd place across three challenges at ACM Multimedia 2026: EgoLink, AffectiveArt, and MPDD-AVG. Details
  • I serve as a Challenge and Data Chair for NeuroMM 2026, the 1st International Workshop on Neurophysiological Intelligence for Human-Aware Multimedia, co-located with ACM Multimedia 2026. Details
  • MME-Emotion was accepted at ICLR 2026. Details
  • AffectGPT was accepted as an oral presentation at ICML 2025. Details
  • Emotion-LLaMA was accepted at NeurIPS 2024. Details

Selected Publications (Full publications)

My name is shown in bold. An asterisk (*) denotes equal contribution.

  1. MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models ICLR 2026

    Fan Zhang*, Zebang Cheng*, Chong Deng*, Haoxuan Li, Zheng Lian, Qian Chen, Huadai Liu, Wen Wang, Yi-Fan 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

    * Equal contribution. A unified benchmark for audio-visual emotion understanding and reasoning.

    Paper Project

  2. AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models ICML 2025

    Zheng Lian, Haoyu Chen, Lan Chen, Haiyang Sun, Licai Sun, Yong Ren, Zebang Cheng, Bin Liu, Rui Liu, Xiaojiang Peng, Jiangyan Yi, Jianhua Tao

    Oral presentation.

    Paper Code

  3. Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning NeurIPS 2024

    Zebang Cheng*, Zhi-Qi Cheng*, Jun-Yan He, Jingdong Sun, Kai Wang, Yuxiang Lin, Zheng Lian, Xiaojiang Peng, Alexander Hauptmann

    * Equal contribution.

    Paper Project Code

  4. MIPS at SemEval-2024 Task 3: Multimodal Emotion-Cause Pair Extraction in Conversations with Multimodal Language Models SemEval 2024

    Zebang Cheng*, Fuqiang Niu*, Yuxiang Lin, Zhi-Qi Cheng, Bowen Zhang, Xiaojiang Peng

    * Equal contribution. 3rd place in the Multimodal Emotion-Cause Analysis Challenge.

    Paper Code

  5. SZTU-CMU at MER2024: Improving Emotion-LLaMA with Conv-Attention for Multimodal Emotion Recognition MRAC at ACM Multimedia 2024

    Zebang Cheng*, Shuyuan Tu*, Dawei Huang*, Minghan Li, Xiaojiang Peng, Zhi-Qi Cheng, Alexander G. Hauptmann

    * Equal contribution. 1st place in MER-NOISE and 3rd place in the Open-Vocabulary Multimodal Emotion Recognition Challenge.

    Paper Code

  6. Semi-Supervised Multimodal Emotion Recognition with Expression MAE ACM Multimedia 2023

    Zebang Cheng, Yuxiang Lin, Zhaoru Chen, Xiang Li, Shuyi Mao, Fan Zhang, Daijun Ding, Bowen Zhang, Xiaojiang Peng

    2nd place in the ACM Multimedia 2023 Multimodal Emotion Recognition Challenge.

    Paper

Education

Shenzhen University & Guangming Laboratory

Ph.D. in Computer Science and Technology

Advised by Prof. Laizhong Cui and Dr. Fei Ma.

2025–Present Shenzhen, China

Shenzhen University & Shenzhen Technology University

M.S. in Computer Science

Advised by Prof. Xiaojiang Peng.

2022–2025 Shenzhen, China

China West Normal University

B.S. in Software Engineering

2017–2021 Nanchong, China

Honors & Awards

Professional Activities