ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling Paper • 2610.15166 • Published 16 days ago • 85
IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring Paper • 2605.24553 • Published May 23 • 25
PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop Paper • 2610.00559 • Published 26 days ago • 69