A new benchmark converts video clips into shared grounded event records and tests models across physics, semantic, and control prompts under original, shuffled, ablated, and masked conditions, finding selective robustness and weak spatial performance.
TAU-R1: Visual language model for traffic anomaly understanding
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Grounding Video Reasoning in Physical Signals
A new benchmark converts video clips into shared grounded event records and tests models across physics, semantic, and control prompts under original, shuffled, ablated, and masked conditions, finding selective robustness and weak spatial performance.