Kimin Lee

DEAS: DEtached value learning with Action Sequence for Scalable Offline RL

Learning to Generate Unit Test via Adversarial Reinforcement Learning

Adversarial Reinforcement Learning Framework for ESP Cheater Simulation

Revisiting Multi-Agent Debate as Test-Time Scaling: When Does Multi-Agent Help?

Toward Self-Evolving Systems of LLM Agents through Exploration and Iterative Feedback

Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment

Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents

Understanding Impact of Human Feedback via Influence Functions

Subtask-Aware Visual Reward Learning from Segmented Demonstrations

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing

Latent Action Pretraining from Videos

Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models

B-MoCA: Benchmarking Mobile Device Control Agents across Diverse Configurations

MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control