Kee-Eung Kim

Group-Normalized Implicit Value Optimization for Language Models

SpoilDICE: Safe and Performant Offline Imitation Learning from Dual Demonstrations

Multimodal Masked Polymer Autoencoder for Unified Polymer Informatics

Agent-Chained Policy Optimization

Monet: Mixture of Monosemantic Experts for Transformers

DPAIL: Training Diffusion Policy for Adversarial Imitation Learning without Policy Optimization

Contrast with Aggregation: A Scalable Framework for Multi-View Representation Learning

CLEAR: An Information-Theoretic Framework for Distraction-Free Representation Learning in Visual Offline RL