2025
From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment
[Preprint Arxiv 2025] Kyubyung Chae, Hyunbin Jin, Taesup Kim
Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and Missingness
[Preprint Arxiv 2025] Jinkwan Jang, Hyungjin Park, Jinmyeong Choi, Taesup Kim
ATAS: Any-to-Any Self-Distillation for Enhanced Open-Vocabulary Dense Prediction
[Preprint Arxiv 2025] Juan Yeo, Soonwoo Cha, Jiwoo Song, Hyunbin Jin, Taesup Kim
Sparse Imagination for Efficient Visual World Model Planning
[Preprint Arxiv 2025] Junha Chun, Youngjoon Jeong, Taesup Kim
Regularized Personalization of Text-to-Image Diffusion Models without Distributional Drift
[Preprint Arxiv 2025] Gihoon Kim, Hyungjin Park, Taesup Kim
Energy-based Preference Optimization for Test-time Adaptation
[Preprint Arxiv 2025] Yewon Han, Seoyun Yang, Taesup Kim
Parameter-Efficient Fine-Tuning with Column Space Projection
[Preprint Arxiv 2025] Junseo Hwang, Wonguk Cho, Taesup Kim
Generalized and Personalized Federated Learning with Foundation Models via Orthogonal Transformations
[Preprint Arxiv 2025] Eun Gyung Kong, Je Won Yeom, Yonghoon Jeon, Taesup Kim
Object-Centric World Model for Language-Guided Manipulation
[ICLR Workshop 2025] Youngjoon Jeong, Junha Chun, Soonwoo Cha, Taesup Kim
"Well, Keep Thinking": Enhancing LLM Reasoning with Adaptive Injection Decoding
[ACL 2025] Hyunbin Jin, Je Won Yeom, Seunghyun Bae, Taesup Kim
Retaining and Enhancing Pre-trained Knowledge in Vision-Language Models with Prompt Ensembling
[WACV 2025] Donggeun Kim, Yujin Jo, Myungjoo Lee, Taesup Kim
2024
Hollowed Net for On-Device Personalization of Text-to-Image Diffusion Models
[NeurIPS 2024] Wonguk Cho, Seokeon Choi, Debasmit Das, Matthias Reisser, Taesup Kim, Sungrack Yun, Fatih Porikli
Model-based Preference Optimization in Abstractive Summarization without Human Feedback
[EMNLP 2024] Jaepill Choi*, Kyubyung Chae*, Jiwoo Song, Yohan Jo, Taesup Kim
Missing Modality Prediction for Unpaired Multimodal Learning via Joint Embedding of Unimodal Models
[ECCV 2024] Donggeun Kim, Taesup Kim
Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information
[NAACL 2024] Kyubyung Chae*, Jaepill Choi*, Yohan Jo, Taesup Kim
2023
Task-agnostic continual reinforcement learning: Gaining insights and overcoming challenges
[CoLLA 2023] Massimo Caccia, Jonas Mueller, Taesup Kim, Laurent Charlin, Rasool Fakoor
Meta-Learning with Adaptive Weighted Loss for Imbalanced Cold-Start Recommendation
[CIKM 2023] Minchang Kim*, Yongjin Yang*, Jung Hyun Ryu, Taesup Kim
Complementary Domain Adaptation and Generalization for Unsupervised Continual Domain Shift Learning
[ICCV 2023] Wonguk Cho, Jinha Park, Taesup Kim
UOTA: Unsupervised Open-Set Task Adaptation Using a Vision-Language Foundation Model
[ICML Workshop 2023] Youngjo Min, Kwangrok Ryoo, Bumsoo Kim, Taesup Kim
Uncertainty-Guided Online Test-Time Adaptation via Meta-Learning
[ICML Workshop 2023] Kyubyung Chae, Taesup Kim
Meta-Learning with a Geometry-Adaptive Preconditioner
[CVPR 2023] Suhyun Kang, Duhun Hwang, Moonjung Eo, Taesup Kim, Wonjong Rhee
Flexible Model Aggregation for Quantile Regression
[JLMR 2023] Rasool Fakoor, Taesup Kim, Jonas Mueller, Alexander J. Smola, Ryan J. Tibshirani
2022
Adaptive Interest for Emphatic Reinforcement Learning
[NeurIPS 2022] Martin Klissarov, Rasool Fakoor, Jonas Mueller, Kavosh Asadi, Taesup Kim, Alexander J. Smola
Faster Deep Reinforcement Learning with Slower Online Network
[NeurIPS 2022] Kavosh Asadi, Rasool Fakoor, Omer Gottesman, Taesup Kim, Michael L. Littman, Alexander J. Smola
FAD-X: Fusing Adapters for Cross-lingual Transfer to Low-Resource Languages
[AACL 2022] Jaeseong Lee, Seung-won Hwang, Taesup Kim
Efficient Task Adaptation by Mixing Discovered Skills
[ICML Workshop 2022] JUNGSUB RHIM, Eunseok Yang, Taesup Kim
Task-Agnostic Continual Reinforcement Learning: In Praise of a Simple Baseline
[RLDM Workshop 2022] Massimo Caccia, Jonas Mueller, Taesup Kim, Laurent Charlin, Rasool Fakoor
서울특별시 관악구 관악로 1, 43동 4층 (서울대학교 데이터사이언스대학원)
43-506, 1 Gwanak-ro, Gwanak-gu, Seoul, Republic of Korea