Byung-Jun Lee

Beyond RAG vs. Long-Context: Learning Distraction-Aware Retrieval for Efficient Knowledge Grounding

SCAD: Super-Class-Aware Debiasing for Long-Tailed Semi-Supervised Learning

Offline Reinforcement Learning with Penalized Action Noise Injection

Explicitly Bounding Q‑Function Estimates for Offline-to-Online Reinforcement Learning

TABS: Strategic Game-Based Multi-Stage Reinforcement Learning Challenge

GraphMind: LLMs as Dynamic Knowledge Builders for Sequential Decision-Making

Actor-Critic without Actor

FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning

Prior-Guided Diffusion Planning for Offline Reinforcement Learning

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations

Semi-gradient DICE for Offline Constrained Reinforcement Learning

Test-Time Adaptation for Online Vision-Language Navigation with Feedback-based Reinforcement Learning

Diffusion-Based Offline RL for Improved Decision-Making in Augmented Single ARC Task

DIAR: Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation