RetoVLA: Reusing Register Tokens for Spatial Reasoning in Vision-Language-Action Models Paper โข 2509.21243 โข Published Sep 25, 2025 โข 1
SPACE-CLIP: Spatial Perception via Adaptive CLIP Embeddings for Monocular Depth Estimation Paper โข 2601.17657 โข Published Jan 25
Text-Aware Image Restoration with Diffusion Models Paper โข 2506.09993 โข Published Jun 11, 2025 โข 45