Profiles2020-2026
Kee-Eung Kim
KAIST AI
18Papers
14Last author
24Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers18
- Group-Normalized Implicit Value Optimization for Language ModelsAuthor 6 of 6ICLR 2026
- DPAIL: Training Diffusion Policy for Adversarial Imitation Learning without Policy OptimizationAuthor 4 of 4NeurIPS 2025
- Monet: Mixture of Monosemantic Experts for TransformersAuthor 3 of 4ICLR 2025
- Stitching Sub-trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RLAuthor 4 of 4AAAI 2024 · 19 citations
- Mitigating Covariate Shift in Behavioral Cloning via Robust Stationary Distribution CorrectionAuthor 6 of 7NeurIPS 2024 · 17 citations
- Data Augmentation with Diffusion for Open-Set Semi-Supervised LearningAuthor 3 of 3NeurIPS 2024 · 4 citations
- Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL PoliciesAuthor 5 of 7ICLR 2024 · 3 citations
- Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RLAuthor 9 of 9ACL 2024 · 1 citation
- Regularized Behavior Cloning for Blocking the Leakage of Past Action InformationAuthor 4 of 4NeurIPS 2023 · 14 citations
- AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction EstimationAuthor 6 of 6NeurIPS 2023 · 11 citations
- Bayesian Multi-Task Transfer Learning for Soft Prompt TuningAuthor 4 of 4EMNLP Findings 2023 · 5 citations
- Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous ActionsAuthor 7 of 9NeurIPS 2022 · 7 citations
- End-to-End Neural Pipeline for Goal-Oriented Dialogue Systems using GPT-2Author 4 of 4ACL 2020 · 167 citations
- Variational Interaction Information Maximization for Cross-domain DisentanglementAuthor 4 of 4NeurIPS 2020 · 65 citations
- Monte-Carlo Tree Search in Continuous Action Spaces with Value GradientsAuthor 4 of 4AAAI 2020 · 24 citations
- Bayes-Adaptive Monte-Carlo Planning and Learning for Goal-Oriented DialoguesAuthor 3 of 3AAAI 2020 · 22 citations
- Reinforcement Learning for Control with Multiple FrequenciesAuthor 3 of 3NeurIPS 2020 · 19 citations
- Batch Reinforcement Learning with Hyperparameter GradientsAuthor 5 of 5ICML 2020 · 18 citations
