ZHANG, Cheng 张成

Available for collaboration · MPhil 2026

MPhil student in Artificial Intelligence at HKUST(GZ), working on multimodal intelligence, large language models, and computer vision.

I am interested in building reliable and human-centered AI systems that connect language, vision, and multimodal reasoning, with a particular focus on multimodal understanding.

EmailGoogle ScholarHKUST(GZ)
Portrait of Zhang Cheng

01 About

I  am an MPhil student in Artificial Intelligence at The Hong Kong University of Science and Technology, Guangzhou Campus, where I am advised by Prof. Hui Xiong (Fellow of ACM/IEEE/AAAI/AAAS/CCF/CAAI) in the AI+ Lab.

Previously, I received my B.Sc. in Computer Science & Technology from Jilin University. During my undergraduate studies, I was a research assistant at the Affective Vision Computing Lab, advised by Prof. Hongxia Xie, and collaborated with Prof. Wen-Huang Cheng from National Taiwan University (Fellow of IEEE and IAPR).

02 Research Interests

Large Language Models

Reasoning, agents, and reliable language-model systems that can generalize beyond static benchmarks.

Multimodal LLMs

Connecting language with visual signals for grounded perception, understanding, and generation.

Computer Vision

Visual representation learning and vision-language methods for challenging real-world scenarios.

LLM Agents

Tool-using, memory-augmented, and multi-step reasoning agents that can plan and act in complex environments.

03 News

  • DatasetOur EmoArt dataset has surpassed 10,000 cumulative downloads on Hugging Face!
  • Newglad to start a new journey as an MPhil student at HKUST(GZ).
  • PaperOne paper accepted to EMR @ ECCV 2026.
  • PaperOne paper accepted to ACL 2026 Main.
  • ServiceLeading organizer of the AffectiveArt Challenge at ACM Multimedia 2026.
  • TalkGave an Oral presentation at ACM Multimedia 2025.
  • PaperEmoArt accepted to ACM Multimedia 2025.

04 Publications

* denotes equal contribution.

  • ACM MM 2025Oral

    EmoArt: A Multidimensional Dataset for Emotion-Aware Artistic Generation

    Zhang Cheng, HongXia Xie, Bin Wen, Songhan Zuo, Ruoxuan Zhang, Wen-Huang Cheng

    ACM International Conference on Multimedia, 2025

    ★ Oral
  • ACL 2026Main

    HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents

    Jinchang Zhu*, Jindong Li*, Zhang Cheng*, Jiahong Liu, Menglin Yang

    Annual Meeting of the Association for Computational Linguistics, 2026

  • TAFFCUnder review

    EmoDiscover: Vocabulary-free Emotion Discovery via Multi-modal Large Language Model

    Hung-Jen Chen, Hongxia Xie, Zhang Cheng, Songhan Zuo, Chu-Jun Peng, Hong-Han Shuai, Yong Man Ro, Wen-Huang Cheng

    IEEE Transactions on Affective Computing

  • CVPR 2026Under review

    AmorisBench: A Comprehensive Multi-modal Dataset for Love-centric Question Answering

    Chu-Jun Peng, Hongxia Xie, Zhang Cheng, Wen-Huang Cheng

    IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026

  • TMMUnder review

    Single Document Image Highlight Removal via A Large-Scale Real-World Dataset and A Location-Aware Network

    Lu Pan, Yu-Hsuan Huang, Hongxia Xie, Zhang Cheng, Hongwei Zhao, Hong-Han Shuai, Wen-Huang Cheng

    IEEE Transactions on Multimedia

05 Education & Experience

  • The Hong Kong University of Science and Technology, Guangzhou Campus

    MPhil in Artificial IntelligenceMPhil Student

  • Jilin University

    B.Sc. in Computer Science & TechnologyAverage score: 89/100 · Rank: 6/102

  • ACL Rolling Review

    ReviewerServed as a reviewer for ARR May 2026.

  • ACM Multimedia 2025

    ReviewerServed as a reviewer.

06 Honors & Awards

  • Postgraduate Scholarship (PGS) — Full scholarship from HKUST(GZ).2026–28
  • Undergraduate Scholarship — Jilin University.2022–25

07 Contact

I am happy to discuss research, collaboration, and opportunities in multimodal intelligence.

ChengZhang0525@gmail.comczhang332@connect.hkust-gz.edu.cngithub.com/ZHILIANGZHANG