16 papers
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…