6 papers
Path-level Hindsight Instructions for Semantic Exploration in Vision-Language Navigation
Sung June Kim, Sangpil Kim, Honglak Lee
On-policy exploration is a crucial component for training robust Vision-Language Navigation agents, as it exposes the policy to a broader state distribution. However, such explorat…
SECOND-Grasp: Semantic Contact-guided Dexterous Grasping
Han Yi Shin, Heeju Ko, Jaewon Mun +6
Achieving reliable robotic manipulation, such as dexterous grasping, requires a synergy between physically stable interactions and semantic task guidance, yet these objectives are…
RevoNAD: Reflective Evolutionary Exploration for Neural Architecture Design
Gyusam Chang, Jeongyoon Yoon, Shin han yi +3
Recent progress in leveraging large language models (LLMs) has enabled Neural Architecture Design (NAD) systems to generate new architecture not limited from manually predefined se…
Text-Aware Image Restoration with Diffusion Models
Jaewon Min, Jin Hyeon Kim, Paul Hyunbin Cho +6
Image restoration aims to recover degraded images. However, existing diffusion-based restoration methods, despite great success in natural image restoration, often struggle to fait…
Active Test-time Vision-Language Navigation
Heeju Ko, Sungjune Kim, Gyeongrok Oh +5
Vision-Language Navigation (VLN) policies trained on offline datasets often exhibit degraded task performance when deployed in unfamiliar navigation environments at test time, wher…
3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation
Gyeongrok Oh, Sungjune Kim, Heeju Ko +7
The resolution of voxel queries significantly influences the quality of view transformation in camera-based 3D occupancy prediction. However, computational constraints and the prac…