publications

publications by categories in reversed chronological order.

2026

  1. agent.png
    Long Live the Librarian! A Persistent Search Sub-Agent for Energy-Efficient Multi-Agent Software Engineering Systems
    Seunghyuk Cho, Sunghyun Choi, Jaeseung Heo, Youngbin Choi, Saemi Moon, and 2 more authors
    In Empirical Methods in Natural Language Processing (EMNLP), 2026
    Paper
  2. unlearning.png
    Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models
    Saemi Moon, Suhyeon Jun, Seoyeon Lee, and Dongwoo Kim
    In Trustworthy AI for Good @ ICML 2026, 2026
    Paper Website
  3. feedback.png
    In-Place Feedback: A New Paradigm for Guiding LLMs in Multi-Turn Reasoning
    Youngbin Choi*, Minjong Lee*, Saemi Moon, Seunghyuk Cho, Chaehyeon Chung, and 2 more authors
    In Empirical Methods in Natural Language Processing (EMNLP), 2026
    In Workshop on Foundations of Deep Generative Models (FoGen) @ ICML 2026
    Paper

2025

  1. evaluation.png
    Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearning
    Saemi Moon*, Minjong Lee*, Sangdon Park, and Dongwoo Kim
    In International Conference on Computer Vision (ICCV), 2025
    Paper Code Website

2024

  1. unlearning.png
    Feature Unlearning for Pre-trained GANs and VAEs
    Saemi Moon, Seunghyuk Cho, and Dongwoo Kim
    In AAAI Conference on Artificial Intelligence (AAAI), 2024
    Outstanding Paper Award at KAIA 2023
    Paper

2023

  1. skeleton.png
    Anonymization for skeleton action recognition
    Saemi Moon*, Myeonghyeon Kim*, Zhenyue Qin, Yang Liu, and Dongwoo Kim
    In AAAI Conference on Artificial Intelligence (AAAI), 2023
    In Trustworthy and Socially Responsible Machine Learning (TSRML) @ NeurIPS 2022
    Paper Code Poster