collaborators

7 papers

cs.AI2026

Efficient Skill Grounding via Code Refactoring with Small Language Models

Sera Choi, Wonje Choi, Saehun Chun +4

Effective skill grounding is essential for deploying reusable skills in embodied agents, as even minor embodiment or environmental differences can render an entire skill incompatib…

cs.LG2026

A Recipe for Stable Offline Multi-agent Reinforcement Learning

Dongsu Lee, Daehee Lee, Amy Zhang

Despite remarkable achievements in single-agent offline reinforcement learning (RL), multi-agent RL (MARL) has struggled to adopt this paradigm, largely persisting with on-policy t…

cs.LG2026

Multi-agent Coordination via Flow Matching

Dongsu Lee, Daehee Lee, Amy Zhang

This work presents MAC-Flow, a simple yet expressive framework for multi-agent coordination. We argue that requirements of effective coordination are twofold: (i) a rich representa…

cs.AI2026

Unifying Agent Interaction and World Information for Multi-agent Coordination

Dongsu Lee, Daehee Lee, Yaru Niu +3

This work presents a novel representation learning framework, *interaction-world* latent (IWoL), to facilitate *team coordination* in multi-agent reinforcement learning (MARL). Bui…

cs.LG2026

Policy Compatible Skill Incremental Learning via Lazy Learning Interface

Daehee Lee, Dongsu Lee, TaeYoon Kwack +2

Skill Incremental Learning (SIL) is the process by which an embodied agent expands and refines its skill set over time by leveraging experience gained through interaction with its…

cs.AI2025

NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains

Wonje Choi, Jinwoo Park, Sanghyun Ahn +2

We explore neuro-symbolic approaches to generalize actionable knowledge, enabling embodied agents to tackle complex tasks more effectively in open-domain environments. A key challe…