AI RESEARCH
The Perception-Physics Paradox: Probing Scientific Alignment with TC-Bench
arXiv CS.LG
•
ArXi:2605.24782v1 Announce Type: new While Vision Foundation Models (VFMs) excel at predictive tasks on satellite imagery, their performance can arise from visual correlations rather than underlying structural invariants, making even perception-based out-of-distribution accuracy a poor proxy for scientific utility. As a result, models may look correct without reasoning correctly, a discrepancy we term the Perception-Physics Paradox. To address this gap, we