7 papers
AxisGuide: Grounding Robot Action Coordinate System in RGB Observations for Robust Visuomotor Manipulation
Jiyun Jang, Yujin Sung, Woosung Joung +5
Visuomotor manipulation policies trained via large-scale behavior cloning have achieved strong semantic scene understanding, yet often fail to reliably execute correct low-level ac…
SODE: Analyzing Social Dynamics in LLM Agents
Inseo Jung, Yoonseok Oh, Kyungryul Back +2
As Large Language Models (LLMs) evolve into interactive agents, understanding their behavioral alignment within human social dynamics becomes essential. While behavioral game theor…
Dynamic In-Group Persona Generation for Enhancing Human-AI Rapport
Yoonseok Oh, Inseo Jung, Jinkyu Kim +3
LLM-based chatbots are increasingly applied in interpersonal domains such as counseling and peer support, where establishing human-AI rapport is crucial yet remains challenging. In…
SemanticControl: A Training-Free Approach for Handling Loosely Aligned Visual Conditions in ControlNet
Woosung Joung, Daewon Chae, Jinkyu Kim
ControlNet has enabled detailed spatial control in text-to-image diffusion models by incorporating additional visual conditions such as depth or edge maps. However, its effectivene…
Scene Graph-Guided Proactive Replanning for Failure-Resilient Embodied Agent
Che Rin Yu, Daewon Chae, Dabin Seo +3
When humans perform everyday tasks, we naturally adjust our actions based on the current state of the environment. For instance, if we intend to put something into a drawer but not…
DiffExp: Efficient Exploration in Reward Fine-tuning for Text-to-Image Diffusion Models
Daewon Chae, June Suk Choi, Jinkyu Kim +1
Fine-tuning text-to-image diffusion models to maximize rewards has proven effective for enhancing model performance. However, reward fine-tuning methods often suffer from slow conv…