Kevin Qinghong Lin

Postdoctoral Researcher

Torr Vision Group
University of Oxford

Email: kevin.qh.lin [at] gmail.com

[Scholar] [Github] [HF] [LinkedIn] [Twitter]


Biography

I am a Postdoctoral Researcher in University of Oxford, working with Prof. Philip Torr.

I obtained my PhD from National University of Singapore in three years, luckily advised by Prof. Mike Shou.

I was fortunate to intern at Tencent / Meta AI / Meta Reality Labs / Microsoft Research.

My research focuses on developing multimodal intelligent agents to assist humans. This spans abilities like:

I’m open to collaborate with academic / industry / startups. Feel free to drop me an email.

I am passionate about open-source!

Selected Publications [Google Scholar]

† indicates equal contribution. Denotes student I mentored. ✉ indicates corresponding author.
Video Reality Test: Can AI-Generated ASMR Videos fool VLMs and Humans?
Jiaqi Wang, Weijia Wu, Yi Zhan, Rui Zhao, Ming Hu, James Cheng, Wei Liu, Philip Torr, Kevin QH. Lin✉

Preprint, 2025
[project] [paper] [code]
#2 Huggingface daily paper.

Computer-Use Agents as Judges for Generative User Interface
Kevin QH. Lin†, Siyuan Hu†, Linjie Li, Zhengyuan Yang, Lijuan Wang, Philip Torr, Mike Z. Shou.

Preprint, 2025
[project] [paper] [code] [demo] [twitter]

VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation
Kevin QH. Lin†, Yuhao Zheng†, Hangyu Ran†, Dantong Zhu, Dongxing Mao, Linjie Li, Philip Torr, Alex JP. Wang.

Preprint, 2025
[project] [paper] [code] [demo] [twitter]
#1 Huggingface daily paper.

Paper2Video: Automatic Video Generation from Scientific Papers
Zeyu Zhu†, Kevin QH. Lin†, Mike Z. Shou.

Preprint, 2025
[project] [paper] [code] [dataset] [twitter]
#2 Huggingface daily paper.
1.9K github stars. 1M+ twitter views. Highlighted by YC Hacker News

Code2Video: A Code-centric Paradigm for Educational Video Generation
Yanzhe Chen†, Kevin QH. Lin†, Mike Z. Shou.

Preprint, 2025
[project] [paper] [code] [dataset] [twitter]
1.4K github stars.

Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers
Wei Pang†, Kevin QH. Lin†, Xiangru Jian†, Xi He, Philip Torr.

NeurIPS D&B, 2025
ICML MAS workshop, 2025. Oral
[project] [paper] [code] [datasets] [demo] [poster] [twitter]
3K github stars. 1.2K twitter likes.

Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
Jiaqi Wang†, Kevin QH. Lin†, James Cheng, Mike Z. Shou.

NeurIPS, 2025
[paper] [code] [huggingface] [twitter]

VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning
Ye Liu†, Kevin QH. Lin†, Chang Wen Chen, Mike Z. Shou.

Preprint, 2025
NeurIPS LAW workshop, 2025. Spotlight
[project] [paper] [code] [dataset] [demo] [twitter]

Grounding Computer Use Agents on Human Demonstrations
Aarash Feizi†, Shravan Nayak†, Xiangru Jian, Kevin QH. Lin, Kaixin Li, Rabiul Awal, Xing Han Lù, Johan Obando-Ceron, Juan A Rodriguez, Nicolas Chapados, David Vazquez, Adriana Romero-Soriano, Reihaneh Rabbany, Perouz Taslakian, Christopher Pal, Spandana Gella, Sai Rajeswar.

Preprint, 2025
[project] [paper] [code] [huggingface] [twitter]
#2 Huggingface daily paper.
The dataset has been downloaded over 150,000 times

UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
Shravan Nayak†, Xiangru Jian†, Kevin QH. Lin, Juan A Rodriguez, Montek Kalsi, Rabiul Awal, Nicolas Chapados, M Tamer Özsu, Aishwarya Agrawal, David Vazquez, Christopher Pal, Perouz Taslakian, Spandana Gella, Sai Rajeswar.

ICML, 2025
[project] [paper] [code] [huggingface] [twitter]

Show-o: One Single Transformer to Unify Multimodal Understanding and Generation
Jinheng Xie†, Weijia Mao†, Zechen Bai†, David JH. Zhang†, Weihao Wang, Kevin QH. Lin, Yuchao Gu, Zhijie Chen, Zhenheng Yang, Mike Z. Shou.

ICLR, 2025
[project] [paper] [code] [huggingface] [demo] [twitter]
1.8K github stars.
Most Influential ICLR Papers #4
AssistGPT: Towards Multi-modal Agent for Human-Centric AI Assistant
Difei Gao, Siyuan Hu, Kevin QH. Lin, Mike Z. Shou.

ACMMM HCMA workshop, 2024. Best Demo Paper
[project] [paper] [twitter]

VideoLLM-online: Online Video Large Language Model for Streaming Video
Joya Chen, Zhaoyang Lv, Shiwei Wu, Kevin QH. Lin, Chenan Song, Difei Gao, Jia-Wei Liu, Ziteng Gao, Dongxing Mao, Mike Z. Shou.

CVPR, 2024
[project] [paper] [VideoLLM-MoD] [code] [dataset] [twitter]
600+ github stars.
ShowUI: One Vision-Language-Action Model for GUI Visual Agent
Kevin QH. Lin, Linjie Li, Difei Gao, Zhengyuan Yang, Shiwei Wu, Zechen Bai, Stan WX. Lei, Lijuan Wang, Mike Z. Shou.

CVPR, 2025
NeurIPS OWA workshop, 2024. Oral
[paper] [code] [huggingface] [dataset] [demo] [twitter]
#1 Huggingface daily paper.
Outstanding Paper Award, NeurIPS Open-World Agents Workshop 2024.
The model has been downloaded for over 240,000 times. 1.6K github stars.

VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary
Kevin QH. Lin, Mike Z. Shou.

CVPR, 2025
[paper] [code] [twitter]
580+ github stars.
VideoGUI: A Benchmark for GUI Automation from Instructional Videos
Kevin QH. Lin, Linjie Li, Difei Gao, Qinchen Wu, Mingyi Yan, Zhengyuan Yang, Lijuan Wang, Mike Z. Shou.

NeurIPS D&B, 2024. Spotlight
[project] [paper] [code] [twitter]

Learning Video Context as Interleaved Multimodal Sequences
Kevin QH. Lin, Pengchuan Zhang, Difei Gao, Xide Xia, Joya Chen, Ziteng Gao, Jinheng Xie, Xuhong Xiao, Mike Z. Shou.

ECCV, 2024
[paper] [code]

UniVTG: Towards Unified Video-Language Temporal Grounding
Kevin QH. Lin, Pengchuan Zhang, Joya Chen, Shraman Pramanick, Difei Gao, Alex JP. Wang, Rui Yan, Mike Z. Shou.

ICCV, 2023
[paper] [code] [demo] [twitter]
370+ github stars.
Egocentric Video-Language Pretraining
Kevin QH. Lin, Alex JP. Wang, M. Soldan, M. Wray, R. Yan, Eric ZC. Xu, D. Gao, R. Tu, W. Zhao, W. Kong, C. Cai, H. Wang, D. Damen, B. Ghanemå, W. Liu, Mike Z. Shou.

NeurIPS, 2022. Spotlight (1.7%)
[project] [paper] [EgoVLPv2] [code] [poster] [twitter] [media]
EgoVis Distinguished Paper Award.
PREMIA Best Student Paper Award, Gold Award.
Double champions in Ego4D & Epic-Kitchens CVPR 2022 challenges.

Honors

Service


Flag Counter

© Kevin