2 papers
cs.CV2026
SPACE-CLIP: Spatial Perception via Adaptive CLIP Embeddings for Monocular Depth Estimation
Taewan Cho, Taeryang Kim, Andrew Jaeyong Choi
Robotic and autonomous systems need dense spatial cues, yet adding a dedicated depth estimator can duplicate visual processing already performed by a multimodal model. CLIP-based d…
cs.RO2025
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…