Jaden Park

- jadenpark[at]cs[dot]wisc[dot]edu

prof_pic.jpg

I am a third year Ph.D. student in Computer Science at UW-Madison under the watchful eyes of prof. Yong Jae Lee.

My research interest lies in improving, understanding, and analyzing deep learning models, both empirically and theoretically. I ultimately envision developing deployable machine learning agents that can solve challenging real-world problems. Currently, I am interested in physical AI, exploration, compositional reasoning, continual learning, robustness and generalization.

Prior to joining UW-Madison, I spent a great time at Krafton AI as a research intern, working closely with prof. Kangwook Lee, prof. Dimitris Papailiopoulos and prof. Ernest K. Ryu. I hold a bachelor’s degree from SNU with summa cum laude in Mathematics and Computer Science along with a minor in Philosophy of Science (link), and was fortunate to be advised by prof. Wonjong Rhee.

📝 You can find my curriculum vitae here.


News


May, 2026 🚀 Excited to be back at Adobe for internship!
Apr, 2026 📄 Our work DocHop and AVS-Bench have been accepted at ICML and DMLR!
Mar, 2026 📄 Our work on material segmentaiton MAOAM has been accepted at SIGGRAPH (conference).
Jan, 2026 📄 Our work on VLM Data Contamination has been accepted at ICLR 2026.
May, 2025 🚀 Starting my internship at Adobe!
Sep, 2024 📚 Starting my Ph.D. at UW-Madison!
May, 2024 📄 Our work on ICL of Mamba+Transformer (MambaFormer) has been accepted at ICML 2024.
Jan, 2024 📄 Our work on Image Clustering (IC|TC) has been accepted at ICLR 2024.
Jun, 2023 🚀 Starting my internship at Krafton AI.

Experience

  1. Adobe Research
    Adobe Research | May 2026 – Present
    San Jose, CA, USA
    Topic: World Action Models
    Advisors: Shraman Pramanick
  2. Adobe Research
    Adobe Research | May 2025 – Jan 2026
    San Jose, CA, USA
    Topic: Material-aware multi-modal segmentation
    Advisors: Michael Fischer , Valentin Deschaintre , Krishna Kumar Singh
  3. Krafton AI
    Krafton AI | June 2023 – Feb 2024
    Seoul, South Korea
    Topic: Image clustering, in-context learning and text-based benchmark generation for agents
    Advisors: Kangwook Lee , Dimitris Papailiopoulos

Selected publications

( * denotes equal contribution.)

  1. arXiv
    colm_expl.png
    Exploration and Exploitation Errors Are Measurable for Language Model Agents
    J.  Park*, J.  Kim*, J.  Jeong*, RD  Nowak, K.  Lee and YJ  Lee
    arXiv Preprint, 2026
    Code Project Page Summary 1 Paper
  2. ICML
    dochop.png
    DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents
    Z.  Yu, L. T. P.  Nguyen, J.  Park, X.  Gu, Z.  He, S.  Lee, R.  Feris and YJ  Lee
    International Conference on Machine Learning (ICML) , 2026
    Paper
  3. SIGGRAPH
    maoam.png
    MAOAM: Unified Object and Material Selection with Vision-Language Models
    J.  Park, V.  Deschaintre, J.  Kuen, K.  Liu, I.  Georgiev, K. K.  Singh, YJ  Lee and M.  Fischer
    ACM SIGGRAPH 2026 Conference Papers , 2026
    Code Project Page Summary 1 Paper
  4. ICLR
    mm-perturb.png
    Contamination Detection for VLMs using Multi-Modal Semantic Perturbation
    J.  Park, M.  Cai, F.  Yao, J.  Shang, S.  Lee and YJ  Lee
    International Conference on Machine Learning (ICLR), 2026
    Code Project Page Summary 1 Paper
  5. DMLR
    avsb.png
    Decomposing Complex Visual Comprehension into Atomic Visual Skills for Vision Language Models
    H.  Chae, S.  Yoon, J.  Park, C. Y.  Chun, Y.  Cho, M.  Cai, YJ  Lee and E. K.  Ryu
    Journal of Data-centric Machine Learning Research, 2025
    Code Summary 1 Paper
  6. arXiv
    TDBench.png
    TemporalBench: Towards Fine-grained Temporal Undestanding for Multimodal Video Models
    M.  Cai, R.  Tan, J.  Zhang, B.  Zou, K.  Zhang, F.  Yao, F.  Zhu, J.  Gu, Y.  Zhong, Y.  Shang, Y.  Dou, J.  Park, J.  Gao, YJ  Lee and J.  Yang
    NeurIPS 2024 Workshop on Video-Language Models (oral), 2024
    Code Project Page Summary 1 Paper
  7. ICML
    icml2024.png
    Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks
    J.  Park, J.  Park, Z.  Xiong, N.  Lee, J.  Cho, S.  Oymak, K.  Lee and D.  Papailiopoulos
    International Conference on Machine Learning (ICML), 2024
    Code Summary 1 Paper
  8. ICLR
    iclr2024.png
    Image Clustering Conditioned on Text Criteria
    S.  Kwon, J.  Park, M.  Kim, J.  Cho, E.  Ryu and K.  Lee
    International Conference on Learning Representations (ICLR), 2024
    Code Summary 1 Summary 2 Paper
  9. RTSS
    rtss.png
    Conditionally Optimal Parallelization of Real-Time DAG Tasks for Global EDF
    Y.  Cho, D.  Shin, J.  Park and C.  Lee
    IEEE Real-Time Systems Symposium (RTSS) , 2021
    Paper