Alan Minchan Kim

profile_image.png

Hi there 👋 I’m Alan.

I am an undergraduate student majoring in Computer Science at Seoul National University, passionate about practical and high-impact research.

My primary research focus lies in the intersection of machine learning, applied cryptography, and computational neuroscience.

I am deeply interested in developing a secure cloud memory system inspired by the human hippocampus—one that continuously gathers, stores, and utilizes an individual’s entire lifetime of egocentric data.

Through this work, I aim to create an AI replica that shares your memories and acts with your intent. To achieve this, the system must (i) securely share your memories, (ii) think, speak, and act like you, and (iii) synchronize with you seamlessly and actively.

More specifically, my research interests include:

  1. Machine Learning
    (a) Secure RAG Framework
    (b) Secure Semantic Search
    (c) Secure Imitation Learning

  2. Applied Cryptography
    (a) Homomorphic Encryption
    (b) Multi-Party Computation
    (c) Private Information Retrieval

  3. Computational Neuroscience
    (a) Principles of How the Hippocampus Stores and Recalls Memories
    (b) Principles of How the Brain Learns and Generalizes Knowledge

If you share these interests or would like to explore potential collaborations, please feel free to reach out!

News

Jul 01, 2024 My co-first author paper ESREAL got accepted to ECCV 2024! :smile:

Selected Publications

  1. esreal_preview.png
    ESREAL: Exploiting Semantic Reconstruction to Mitigate Hallucinations in Vision-Language Models
    Minchan Kim†, Minyeong Kim†, Junik Bae†, and 3 more authors
    European Conference on Computer Vision (ECCV) 2024
  2. canvas_preview.png
    CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction
    Suhwan Choi†, Yongjun Cho†, Minchan Kim†, and 9 more authors
    Conference on Neural Information Processing Systems (NeurIPS) 2024 Workshop OWA (Outstanding Paper Award)
  3. cupid_preview.png
    CUPID: A Real-Time Session-Based Reciprocal Recommendation System for a One-on-One Social Discovery Platform
    Beomsu Kim†, Sangbum Kim†, Minchan Kim†, and 7 more authors
    International Conference on Data Mining (ICDM) 2024 Worshop DMU2
† : equal contribution