5 papers
MIM-VLA: Learning Physical Interaction Representations from Gripper Motor Feedback
Jaeyoung Lee, Jiyeon Koo, Taehwa Kim +2
Vision-language-action (VLA) policies infer grasp actions primarily from visual observations and robot state, but do not explicitly represent the physical response observed after c…
SPACE-CLIPv2: Decoding Local Geometry from Frozen CLIP for Monocular Depth Estimation
Hyun Song, Taewan Cho, Kangmin Kim +1
Vision-language foundation models such as CLIP provide strong semantic representations, but their patch tokens are not directly optimized for dense metric geometry. SPACE-CLIP show…
GeoBridge-VLA: Geometry-Aware Residual Adaptation for Vision-Language-Action Models
Hyun Song, Kangmin Kim, Loren Jinsoo Um +4
Vision-language-action (VLA) models encode semantic information from vision-language pretraining, but manipulation also requires precise spatial reasoning. We present GeoBridge-VLA…
EdgeZSAD: Practical Zero-Shot Anomaly Detection on Edge Devices
Taewan Cho, Andrew Jaeyong Choi
Industrial inspection needs zero-shot anomaly detection (ZSAD) that remains useful under edge deployment constraints. Recent methods often rely on ViT-L foundation backbones (~300M…
RetoVLA: Reusing Register Tokens for Spatial Reasoning in Vision-Language-Action Models
Jiyeon Koo, Taewan Cho, Hyunjoon Kang +4
Vision-Language-Action (VLA) models have demonstrated robust performance across diverse robotic tasks. However, their high memory and computational demands often limit real-time de…