Cheng Zhang

About Me

I am an undergraduate researcher at Jilin University, passionate about advancing artificial intelligence. My research centers on the intersection of Multi-Modal Large Language Models, Computer Vision, and Affective Computing.

I am driven by the challenge of building systems that can holistically perceive, reason, and interact with the world. My work involves creating models that seamlessly integrate diverse data modalities, exploring how machines can achieve a deeper understanding of visual information, and ultimately bridging the gap between computational and emotional intelligence.

News

• I will be visiting Yonsei University, Korea for a collaborative project.

• EmoArt has been accepted and will be published in the main conference proceedings. Looking forward to seeing you in Ireland!🎉

• Our dataset has surpassed 1,000 downloads! 🎉

Skills

Publications

• EmoArt: A Multidimensional Dataset for Emotion-Aware Artistic Generation

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

  Accepted, and will be published in the proceedings of the main conference of ACM MM 2025.

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

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

  Under 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, Cheng Zhang, Hongwei Zhao, Hong-Han Shuai, Wen-Huang Cheng

  Under Review

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

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

  Under Review

Research Experience

• Affective Vision Computing (AVC) Lab, Jilin University

  2024 – Present

  Role: Research Assistant | Supervisor: A/Prof. Hongxia Xie

  Contributing to projects in affective computing and multi-modal machine learning. Developing novel methods to understand and model emotional responses from visual and textual data.

• National & Provincial Research Projects

  Jan 2025 – Present

  Role: Participant

  Participating in two key projects: (1) A National Natural Science Foundation Youth Project on eliminating emotion hallucination in V-L models, and (2) A Jilin Provincial Excellent Youth Project on enhancing emotion understanding stability in multimodal large models.

Education

• Jilin University 985 & 211 Double First-Class ARWU 101-150 US News 296

  2022 – 2026 (Expected)

  B.Sc. in Computer Science & Technology

  GPA: 3.54/4.0 | Rank: 7/102 | Average Score: 88/100

Tutorials

• Reinforcement Learning: A Brief Guide

• A brief introduction to vibe coding (Chinese)

Honors & Awards

• Undergraduate Scholarship, Jilin University

  2024 – 2025

• Undergraduate Scholarship, Jilin University

  2023 – 2024

• Undergraduate Scholarship, Jilin University

  2022 – 2023