1 citations · 1 across the 21 of their papers we have counts for
25 papers
Code-as-Auditor: Executable Compliance Reasoning via Regulation-to-Code
Jisoo Kim, Taeyoon Kwack, Jinwoo Jang +2
Large Language Models (LLMs) are increasingly adopted for compliance and legal reasoning tasks, yet their outputs often lack explicit grounding in legal logic and evidence. We pres…
Visual Compliance via Executable Safety Rule Entailment
Jisoo Kim, TaeYoon Kwack, Jinwoo Jang +1
Recent advances in LLMs and VLMs have enabled safety systems to reason beyond simple risk patterns toward more contextual and semantic safety concerns. However, as risk patterns co…
RoboBRIDGE: A Modular Framework for Bridging Policies to Robust Real-World Robotic Agents
Sihyung Yoon, Minjong Yoo, Sanghyun Ahn +2
Vision-Language-Action (VLA) models have attracted growing interest as a scalable approach to robotic manipulation. While these models are effective action predictors, deploying th…
Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents
Saehun Chun, Wonje Choi, Sera Choi +2
Code-writing large language models (CodeLLMs) generate executable code policies for embodied agents by translating natural language goals and environmental constraints into structu…
Multi-scale Mixture of World Models for Embodied Agents in Evolving Environments
Jinwoo Jang, Daniel J. Rho, Sihyung Yoon +2
Embodied agents operating in the real world require multi-scale reasoning and knowledge adaptation as conditions change. We identify two challenges in applying Mixture of Experts (…
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…
Cross-Domain Demo-to-Code via Neurosymbolic Counterfactual Reasoning
Jooyoung Kim, Wonje Choi, Younguk Song +1
Recent advances in Vision-Language Models (VLMs) have enabled video-instructed robotic programming, allowing agents to interpret video demonstrations and generate executable contro…
Test-Time Mixture of World Models for Embodied Agents in Dynamic Environments
Jinwoo Jang, Minjong Yoo, Sihyung Yoon +1
Language model (LM)-based embodied agents are increasingly deployed in real-world settings. Yet, their adaptability remains limited in dynamic environments, where constructing accu…
Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning
Sanghyun Ahn, Wonje Choi, Junyong Lee +2
Recent advances in large language models (LLMs) have enabled the automatic generation of executable code for task planning and control in embodied agents such as robots, demonstrat…
NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning
Wonje Choi, Jooyoung Kim, Honguk Woo
We address the challenge of adopting language models (LMs) for embodied tasks in dynamic environments, where online access to large-scale inference engines or symbolic planners is…
Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following
Minjong Yoo, Jinwoo Jang, Wei-jin Park +1
This study presents an Exploratory Retrieval-Augmented Planning (ExRAP) framework, designed to tackle continual instruction following tasks of embodied agents in dynamic, non-stati…
In-Context Policy Adaptation via Cross-Domain Skill Diffusion
Minjong Yoo, Woo Kyung Kim, Honguk Woo
In this work, we present an in-context policy adaptation (ICPAD) framework designed for long-horizon multi-task environments, exploring diffusion-based skill learning techniques in…
World Model Implanting for Test-time Adaptation of Embodied Agents
Minjong Yoo, Jinwoo Jang, Sihyung Yoon +1
In embodied AI, a persistent challenge is enabling agents to robustly adapt to novel domains without requiring extensive data collection or retraining. To address this, we present…
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…
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…
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…
Embodied CoT Distillation From LLM To Off-the-shelf Agents
Wonje Choi, Woo Kyung Kim, Minjong Yoo +1
We address the challenge of utilizing large language models (LLMs) for complex embodied tasks, in the environment where decision-making systems operate timely on capacity-limited,…
LLM-Based Offline Learning for Embodied Agents via Consistency-Guided Reward Ensemble
Yujeong Lee, Sangwoo Shin, Wei-Jin Park +1
Employing large language models (LLMs) to enable embodied agents has become popular, yet it presents several limitations in practice. In this work, rather than using LLMs directly…
Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation
Daehee Lee, Minjong Yoo, Woo Kyung Kim +2
Continual Imitation Learning (CiL) involves extracting and accumulating task knowledge from demonstrations across multiple stages and tasks to achieve a multi-task policy. With rec…
Pareto Inverse Reinforcement Learning for Diverse Expert Policy Generation
Woo Kyung Kim, Minjong Yoo, Honguk Woo
Data-driven offline reinforcement learning and imitation learning approaches have been gaining popularity in addressing sequential decision-making problems. Yet, these approaches r…
Offline Policy Learning via Skill-step Abstraction for Long-horizon Goal-Conditioned Tasks
Donghoon Kim, Minjong Yoo, Honguk Woo
Goal-conditioned (GC) policy learning often faces a challenge arising from the sparsity of rewards, when confronting long-horizon goals. To address the challenge, we explore skill-…
Semantic Skill Grounding for Embodied Instruction-Following in Cross-Domain Environments
Sangwoo Shin, Seunghyun Kim, Youngsoo Jang +2
In embodied instruction-following (EIF), the integration of pretrained language models (LMs) as task planners emerges as a significant branch, where tasks are planned at the skill…
Model Adaptation for Time Constrained Embodied Control
Jaehyun Song, Minjong Yoo, Honguk Woo
When adopting a deep learning model for embodied agents, it is required that the model structure be optimized for specific tasks and operational conditions. Such optimization can b…
Robust Policy Learning via Offline Skill Diffusion
Woo Kyung Kim, Minjong Yoo, Honguk Woo
Skill-based reinforcement learning (RL) approaches have shown considerable promise, especially in solving long-horizon tasks via hierarchical structures. These skills, learned task…