MMHNet enables video-to-audio models trained on short clips to generalize and generate audio for videos over 5 minutes long.
Titan-guide: Taming inference-time alignment for guided text-to-video diffusion models
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
-
Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models
MMHNet enables video-to-audio models trained on short clips to generalize and generate audio for videos over 5 minutes long.