Jihyung Kil

Research Scientist

Maryland

Jihyung is a Research Scientist at Adobe Research. He earned his Ph.D. in Computer Science and Engineering from The Ohio State University, working with Wei-Lun Chao. Prior to Adobe, he interned at Google Research and Amazon Alexa AI. His research interests include Vision and Language, with a recent focus on multimodal document understanding and web/UI agents. Check his personal website for more details.

Feel free to contact him at jkil@adobe.com for university collaborations and internships.

Publications

DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning

Choi, Joonmyung., Lee, Sanghyeok., Kim, Jongha., Kim, Sehyung., Ko, Dohwan., Kil, Jihyung., Kim, Hyunwoo. (Jun. 3, 2026)

Conference on Computer Vision and Pattern Recognition (CVPR 2026)

Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations

Li, Zichao., Wu, Gang., Wang, Jack., Zhang, Ruiyi., Zhu, Wanrong., Rossi, Ryan., Morariu, Vlad., Kil, Jihyung. (Apr. 25, 2026)

International Conference on Learning Representations (ICLR 2026)

Representation Shift: Unifying Token Compression with FlashAttention

Choi, Joonmyung., Lee, Sanghyeok., Ko, Byungoh., Kim, Eunseo., Kil, Jihyung., Kim, Hyunwoo. (Oct. 19, 2025)

International Conference on Computer Vision (ICCV 2025)

Click, Type, Repeat: A Comprehensive Survey on GUI Agents

Nguyen, Dang., Chen, Jian., Wang, Yu., Wu, Gang., Park, Namyong., Hu, Zhengmian., Lyu, Hanjia., Wu, Junda., Aponte, Ryan., Xia, Yu., Li, Xintong., Shi, Jing., Chen, Hongjie., Lai, Viet., Xie, Zhouhang., Kim, Sungchul., Zhang, Ruiyi., Yu, Tong., Tanjim, Mehrab., Ahmed, Nesreen., Mathur, Puneet., Yoon, David., Yao, Lina., Kveton, Branislav., Kil, Jihyung., Nguyen, Thien., Bui, Trung., Zhou, Tianyi., Rossi, Ryan., Dernoncourt, Franck. (Aug. 1, 2025)

ACL 2025 Findings