Function2Scene: 3D Indoor Scene Layout from Functional Specifications Paper • 2605.30819 • Published 5 days ago • 36
ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning Paper • 2604.24300 • Published Apr 27 • 67
Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning Paper • 2506.13654 • Published Jun 16, 2025 • 44