← Search

Daehee Lee

7 accepted papers

2026

Efficient Skill Grounding via Code Refactoring with Small Language Models

ICML 2026poster

Effective skill grounding is essential for deploying reusable skills in embodied agents, as even minor embodiment or environmental differences can render an entire skill incompatible. This challenge is particularly pronounced in embodied settings, where agents must operate in dynamic, partially obse…

Cited by 0SourceScholar
2025

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

ICLR 2025poster

We explore neuro-symbolic approaches to generalize actionable knowledge, enabling embodied agents to tackle complex tasks more effectively in open-domain environments. A key challenge for embodied agents is the generalization of knowledge across diverse environments and situations, as limited experi…

Cited by 0SourcePDFScholar
2025

Policy Compatible Skill Incremental Learning via Lazy Learning Interface

NeurIPS 2025spotlight

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 environment or by the integration of additional data. SIL facilitates efficient acquisition of hierarchical policies gro…

Cited by 0SourceScholar
2024

Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation

NeurIPS 2024poster

Continual Imitation Learning (CiL) involves extracting and accumulating task knowledge from demonstrations across multiple stages and tasks to achieve a multi-task policy. With recent advancements in foundation models, there has been a growing interest in adapter-based CiL approaches, where adapters…

Cited by 5SourcePDFScholar
2023

One-shot Imitation in a Non-Stationary Environment via Multi-Modal Skill

ICML 2023poster

One-shot imitation is to learn a new task from a single demonstration, yet it is a challenging problem to adopt it for complex tasks with the high domain diversity inherent in a non-stationary environment. To tackle the problem, we explore the compositionality of complex tasks, and present a novel s…

Cited by 8SourcePDFScholar
2023

Separable and Recombinable Magnetic Robot for Robotic Endovascular Intervention

RA-L 2023

This study presents a separable and recombinable magnetic robot (SRMR) to deliver and retrieve an untethered magnetic robot (UMR) to a target vascular lesion safely and effectively for robotic endovascular intervention. The SRMR comprises a delivery catheter and UMR connected to the end of the deliv

Cited by 21SourceScholar