2024
Model-based Preference Optimization in Abstractive Summarization without Human Feedback
J Choi*, K Chae*, J Song, Y Jo, T Kim
EMNLP 2024 (main / long)
Modality Prediction for Unpaired Multimodal Learning via Joint Embedding of Unimodal Models
D Kim, T Kim
ECCV 2024
Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information
K Chae*, J Choi*, Y Jo, T Kim
NAACL 2024 (findings)
2023
Meta-Learning with Adaptive Weighted Loss for Imbalanced Cold-Start Recommendation
M Kim, Y Yang, J Ryu, T Kim
CIKM 2023
Complementary Domain Adaptation and Generalization for Unsupervised Continual Domain Shift Learning
W Cho, J Park, T Kim
ICCV 2023
UOTA: Unsupervised Open-Set Task Adaptation Using a Vision-Language Foundation Model
Y Min, K Ryoo, B Kim, T Kim
ICML Workshop 2023 on Efficient Systems for Foundation Models
Uncertainty-Guided Online Test-Time Adaptation via Meta-Learning
K Chae, T Kim
ICML Workshop 2023 on Spurious Correlations, Invariance, and Stability
Meta-Learning with a Geometry-Adaptive Preconditioner
S Kang, D Hwang, M Eo, T Kim, W Rhee
CVPR 2023
Flexible Model Aggregation for Quantile Regression
R Fakoor, T Kim, J Mueller, AJ Smola, RJ Tibshirani
JLMR vol24.
2022
Adaptive Interest for Emphatic Reinforcement Learning
M Klissarov, R Fakoor, J Mueller, K Asadi, T Kim, A Smola
NeurIPS 2022
Faster Deep Reinforcement Learning with Slower Online Network
K Asadi, R Fakoor, O Gottesman, T Kim, ML Littman, AJ Smola
NeurIPS 2022
FAD-X: Fusing Adapters for Cross-lingual Transfer to Low-Resource Languages
J Lee, S Hwang, T Kim
AACL 2022
Efficient Task Adaptation by Mixing Discovered Skills
E Yang, J Rhim, T Kim
Pre-training Workshop at ICML 202
Task-Agnostic Continual Reinforcement Learning: In Praise of a Simple Baseline
M Caccia, J Mueller, T Kim, L Charlin, R Fakoor
arXiv preprint arXiv:2205.14495