Younggyo Seo

HAMLET: Switch Your Vision-Language-Action Model into a History-Aware Policy

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

Contrastive Representation Regularization for Vision-Language-Action Models

ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context

RoboAlign: Reinforcement Learning for Action-Aligned Multimodal Large Language Models

Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning

Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics

Reinforcement Learning with Action Sequence for Data-Efficient Robot Learning