4 papers
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…
VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data
Thomas Zeng, Shuibai Zhang, Shutong Wu +13
Process Reward Models (PRMs) have proven effective at enhancing mathematical reasoning for Large Language Models (LLMs) by leveraging increased inference-time computation. However,…