Guanyu Zhou

Guanyu Zhou

Into the New World

About Me

I’m Guanyu Zhou, an undergrad interested in artificial intelligence. Here is my CV.

I am currently working as a research intern on VLM, advised by Professor Zhuang Liu at Princeton University. My current research interests are VLMs (Understanding, Generation, and Reasoning), with a current focus on data. I hope to learn from VLMs, reflect on its bottlenecks, and explore the prototype of the next generation of intelligent systems.

Prior to this, I did a research internship at the NLPGroup of HKUST(GZ), exploring the perceptual flaws of MLLMs. I also had an unforgettable research time at AIMlab, where I worked on problems related to video understanding / action recognition.

My ultimate goal is to build a multimodal, scalable, dataset-free, continuously learning, and self-iterating intelligent system. Feel free to email me to discuss issues in related fields!😄


📅 News

  • [2025.11] OmniDPO accepted by AAAI 2026.
  • [2025.03] I made a sharing at AI TIME, welcome to watch!
  • [2025.01] Our paper CausalMM has been accepted to ICLR 2025, see you in Singapore!
  • [2024.07] I am visiting HKUST(GZ) under the supervision of Professor Xuming Hu!


📝 Publications

Flowchart

[ICLR 2025] Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality

Guanyu Zhou, Yibo Yan, Xin Zou, Kun Wang, Aiwei Liu, Xuming Hu

Flowchart

[AAAI 2026] OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination

Junzhe Chen, Tianshu Zhang, Shiyu Huang, Yuwei Niu, Chao Sun, Rongzhou Zhang, Guanyu Zhou, Lijie Wen, Xuming Hu

Flowchart

CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation

Mingzhe Zheng, Dingjie Song, Guanyu Zhou, Jun You, Jiahao Zhan, Xuran Ma, Xinyuan Song, Ser-Nam Lim, Qifeng Chen, Harry Yang

Flowchart

OccludeNet: A Causal Journey into Mixed-View Actor-Centric Video Action Recognition under Occlusions

Guanyu Zhou, Wenxuan Liu, Wenxin Huang, Xuemei Jia, Xian Zhong, Chia-Wen Lin


📇 Experience

HKUST

[2024.7] HKUST(GZ) / AI Thrust

Topic: Bias in Model Prior Knowledge

AIMLab

[2023.7] AIMLab / Action Recogniton Group

Topic: Bias in the Data (Learning Process)


✍ Services

Reviewer

  • IEEE International Conference on Computer Vision 2025
  • IEEE International Conference on Multimedia & Expo 2025

Management

  • Deputy Director of Competition Management Center of the School’s Innovation and Entrepreneurship Department (2023-2024)


👨‍🏫 Talks