AV-Phys Bench shows that current joint audio-video models lack robust physical commonsense, with major drops on transitions and deliberate anti-physics prompts.
would normally be audible if real-world physics held; answer Yes if they are appropriately represented as such (typically silent here)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Do Joint Audio-Video Generation Models Understand Physics?
AV-Phys Bench shows that current joint audio-video models lack robust physical commonsense, with major drops on transitions and deliberate anti-physics prompts.