Adding a dispersion loss plus a bounded cross-modal drift penalty to intermediate embeddings improves unimodal and multimodal accuracy across audio-visual, image-text, and RF benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Diverse via bounded Agreement: Geometric Regularization for Multimodal Fusion
Adding a dispersion loss plus a bounded cross-modal drift penalty to intermediate embeddings improves unimodal and multimodal accuracy across audio-visual, image-text, and RF benchmarks.