I am a third-year computer science PhD student at Vislang Lab, Rice University, advised by Prof. Vicente Ordóñez. Prior to this, I obtained a BSc degree (First Class Honours) from City University of Hong Kong, where I had the privilege of working with Prof. Rynson W.H. Lau and Prof. Antoni B. Chan.

My primary research interests lie in computer vision, with a focus on efficient algorithms under less or multimodal supervision. During my PhD, I have worked on multimodal understanding and reasoning with RL, efficient generative models for images and videos, and multi-agent systems for UI navigation.

I will graduate in May 2027 and am actively looking for full-time research roles in industry. Do not hesitate to reach out if you would like to chat!

News

[01/2026] I joined ByteDance as a research scientist intern.
[09/2025-01/2026] I will serve as a reviewer for ICLR 2026, CVPR 2026, and ECCV 2026.
[07/2025] Our paper “Learning from Synthetic Data for Visual Grounding” is accepted to BMVC 2025.
[05/2025] I joined Amazon AWS AI Labs as a research intern this summer.
[05/2025] I have been recognized as an Outstanding Reviewer at CVPR 2025.
[08/2024-03/2025] I will serve as a reviewer for T-PAMI, IJCV, ICLR 2025, CVPR 2025, ICML 2025, ICCV 2025, and NeurIPS 2025.
[11/2024] I have been awarded the Ken Kennedy Institute 2024/25 Ken Kennedy-HPE Cray Graduate Fellowship.
[11/2024] I have been recognized as a top reviewer at NeurIPS 2024.
[02/2024] Our paper “Improved Visual Grounding through Self-Consistent Explanations” is accepted to CVPR 2024.
[08/2023-05/2024] I will serve as a reviewer for ICLR 2024, CVPR 2024, ICML 2024, ECCV 2024, and NeurIPS 2024.
[08/2023] I started my PhD study at VisLang Lab, Rice University.
[08/2023] I won the first runner-up prize in the IEEE (Hong Kong) Computational Intelligence Chapter Final Year Project Competition 2022-2023.
[06/2023] I graduated from City University of Hong Kong with First Class Honours.

Education

2023 - 2027 (Expected), PhD in Computer Science, Rice University.
2019 - 2023, BSc in Computer Science (First Class Honours), City University of Hong Kong.

Work Experience

Jan 2026 - Present, Research Scientist Intern, ByteDance (NextGen Recommendation Team @ TikTok Data).
May 2025 - Nov 2025, Applied Scientist Intern, Amazon AWS AI Labs (Amazon Quick Science Team @ Agentic AI).

Preprints

Beyond Referring Expressions: Scenario Comprehension Visual Grounding [Paper] [Project Page]
Ruozhen He, Nisarg A. Shah, Qihua Dong, Zilin Xiao, Jaywon Koo, Vicente Ordonez
April, 2026.

NoiseShift: Resolution-Aware Noise Recalibration for Better Low-Resolution Image Generation [Paper]
Ruozhen He, Moayed Haji-Ali, Ziyan Yang, Vicente Ordonez
October, 2025.

GViT: Representing Images as Gaussians for Visual Recognition [Paper]
Jefferson Hernandez, Ruozhen He, Guha Balakrishnan, Alexander C. Berg, Vicente Ordonez
June, 2025.

Fairness and Bias Mitigation in Computer Vision: A Survey [Paper]
Sepehr Dehdashtian*, Ruozhen He*, Yi Li, Guha Balakrishnan, Nuno Vasconcelos,
Vicente Ordonez, Vishnu Naresh Boddeti (*Joint First Authors)
August, 2024.

Publications

Hierarchical Visual Agent: Managing Contexts in Joint Image-Text Space for Advanced Chart Reasoning
Qihua Dong, Ruozhen He, Junwen Chen, Yizhou Wang, Xu Ma, Songyao Jiang, Yun Fu
The Findings of the Annual Meeting of the Association for Computational Linguistics. ACL Findings, 2026.

Learning from Synthetic Data for Visual Grounding [Paper] [Project Page]
Ruozhen He, Ziyan Yang, Paola Cascante-Bonilla, Alexander C. Berg, Vicente Ordóñez
The British Machine Vision Conference. BMVC 2025.

CVPR 2024 Paper Improved Visual Grounding through Self-Consistent Explanations

Improved Visual Grounding through Self-Consistent Explanations [Paper] [Code] [Project Page]
Ruozhen He, Paola Cascante-Bonilla, Ziyan Yang, Alexander C. Berg, Vicente Ordóñez
The IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR 2024.

AAAI-23 Paper Weakly-Supervised Camouflaged Object Detection with Scribble Annotations

Weakly-Supervised Camouflaged Object Detection with Scribble Annotations [Paper] [Code] [Dataset]
Ruozhen He*, Qihua Dong*, Jiaying Lin, Rynson W.H. Lau (*Joint First Authors)
Proceedings of the AAAI Conference on Artificial Intelligence. AAAI-23. (~Oral Presentation)

AAAI-23 Paper Efficient Mirror Detection via Multi-level Heterogeneous Learning

Efficient Mirror Detection via Multi-level Heterogeneous Learning [Paper] [Code]
Ruozhen He, Jiaying Lin, Rynson W.H. Lau
Proceedings of the AAAI Conference on Artificial Intelligence. AAAI-23. (~Oral Presentation)

Service