MST-Distill claims state-of-the-art cross-modal distillation with a mixture of teachers and dynamic routing, but its teacher-masking stage is fit to the student, creating a circular distillation loop.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
MST-Distill: Mixture of Specialized Teachers for Cross-Modal Knowledge Distillation
MST-Distill claims state-of-the-art cross-modal distillation with a mixture of teachers and dynamic routing, but its teacher-masking stage is fit to the student, creating a circular distillation loop.