|
Violet Fu Yiwei Lyu . Before joining UMich, I earned my M.S. in Artificial Intelligence from Seoul National University, where I had the privilege of being advised by Prof. Gunhee Kim in the Vision & Learning Laboratory. My research aims to build multimodal agents for the real world. Because the world may be far bigger than any model or dataset, real-world agents must generalize robustly, adapt flexibly, and keep learning after deployment. My recent work develops scalable methods that learn computer-use agents from unlabeled videos in the wild. In the long run, I am fascinated by the cycle between abstraction and realization, and by how each expands the boundary between the known and the unknown. (Last updated on: Jul 16, 2026)
Email: yedasong __AT__ umich.edu / |
|
|
|
|
|
Yunseok Jang*, CVPR, 2025 CVPR Workshop on What is Next in Multimodal Foundation Models?, 2025 CODE / arXiv / Data / Project We introduce the MONDAY, a large-scale dataset of 313K annotated frames from 20K instructional videos capturing diverse real-world mobile OS navigation across multiple platforms. Models that include MONDAY in their pretraining phases demonstrate robust cross-platform generalization capabilities. |
|
Yunseok Jang*, NeurIPS Workshop on Video-Language Models, 2024 Non-Archival We introduce MOTIFY, a method for predicting scene transitions and actions from mobile operating system (OS) task videos. It extracts task sequences from YouTube videos without manual annotation, outperforming baselines on Android and iOS tasks and enabling scalable mobile agent development. |
|
ICLR, 2024 CODE / arXiv We propose COCOA, a novel approach for addressing distributional shifts in offline RL (batch RL). COCOA encourages conservatism within the compositional input space of both the policy and Q-function, independently of the commonly employed behavioral conservatism. |
|
Jaewoo Ahn, ACL, 2023 CODE / arXiv We construct a multimodal persona-grounded dialogue dataset, MPChat, accompanied with entailment labels. The multimodal persona consists of image-text pairs that represent one's episodic memories. We show the role of visual modality is crucial in MPChat through three benchmark tasks. |
|
|
|
Ph.D. student in Computer Science & Engineering |
Aug. 2024 - Current |
|
M.S. in Artificial Intelligence |
Mar. 2022 - Feb. 2024 |
|
B.S. in Statistics B.S. in Artificial Intelligence |
Mar. 2017 - Feb. 2022 |
|
Exchange Student |
Fall 2019 |
|
|
Mar. 2014 - Feb. 2017 |
|
|
|
Research Intern |
Jul. 2025 - Dec. 2025 |
|
Machine Learning Researcher |
Jun. 2021 - Aug. 2021 |
|
Research Intern |
Mar. 2021 - Jun. 2021 |
|
Research Intern |
Jan. 2020 - Jun. 2020 |
|
|
|
|
Mar. 2022 - Feb. 2024 |
|
|
Mar. 2017 - Feb. 2021 |
|
|
Mar. 2015 - Feb. 2017 |
|
This website is built with Jon Barron's template. |