AVSD improves self-distillation by identifying cross-view consensus signals and selectively incorporating aligned view-specific residuals for token-level supervision.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
AVSD improves self-distillation by identifying cross-view consensus signals and selectively incorporating aligned view-specific residuals for token-level supervision.