Minchan Kim

profile.jpeg

“I’m looking for Ph.D. positions for Fall 2026.”

I am an undergraduate student in Computer Science at Seoul National University. I am currently working in SNU Vision & Learning Lab, advised by Prof. Gunhee Kim. I have also had the opportunity to collaborate on research with Prof. Yejin Choi at Stanford and Prof. Niloofar Mireshghallah, Prof. Akari Asai, and Prof. Graham Neubig at CMU.

My research centers on advancing machine learning systems for personal intelligence with a strong emphasis on security and privacy. Specifically, my research interests include (1) recording individuals’ everyday lives as permanent data, (2) developing long-term memory systems for these multimodal records, (3) training imitation agents to learn their own cognitive and behavioral dynamics, and (4) ensuring security and privacy in both long-term memory systems and imitation agent training.

My mission is to help people archive their unique life trajectories and create AI clones that can act on their behalf, enabling them to exist beyond the limits of space and time.

News

Jan 26, 2026 Our paper D2E got accepted to ICLR 2026! :smile:
Oct 13, 2025 Our paper D2E just hit #1 on Hugging Face Daily Papers! :smile:
Jun 30, 2025 Our paper PPMI got accepted to Crypto 2025 Workshop! :smile:
Jan 28, 2025 Our paper CANVAS got accepted to ICRA 2025! :smile:
Dec 15, 2024 Our paper CANVAS won the Outstanding Paper Award at NeurIPS 2024 Workshop! :smile:
Sep 30, 2024 Our paper CUPID got accepted to ICDM 2024 Workshop! :smile:
Jul 01, 2024 Our paper ESREAL got accepted to ECCV 2024! :smile:

Publications

† : equal contribution
  1. mipbench_preview.png
    MIP-Bench: Can LLMs Implicitly Personalize Answers for Different Users by Implicitly Leveraging Long-Term Memory?
    Minyeong KimMinchan Kim, Seungone Kim, and 6 more authors
    Under Review
  2. ppmi_preview.png
    PPMI: Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases
    Yubeen BaeMinchan Kim, Jaejin Lee, and 4 more authors
    Under Review, Crypto 2025 Workshop
  3. costnav_preview2.png
    CostNav: A Navigation Benchmark for Cost-Aware Evaluation of Embodied Agents
    Haebin Seong, Sungmin Kim, Minchan Kim, and 10 more authors
    Under Review
  4. d2e_preview.png
    D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI
    Suhwan Choi, Jaeyoon Jung, Haebin Seong, and 7 more authors
    ICLR 2026
  5. canvas_preview2.png
    CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction
    Suhwan Choi, Yongjun ChoMinchan Kim, and 9 more authors
    ICRA 2025, NeurIPS 2024 Workshop (Outstanding Paper Award)
  6. esreal_preview2.png
    ESREAL: Exploiting Semantic Reconstruction to Mitigate Hallucinations in Vision-Language Models
    Minchan Kim, Minyeong Kim, Junik Bae, and 3 more authors
    ECCV 2024
  7. cupid_preview3.png
    CUPID: A Real-Time Session-Based Reciprocal Recommendation System for a One-on-One Social Discovery Platform
    Beomsu Kim, Sangbum KimMinchan Kim, and 7 more authors
    ICDM 2024 Workshop