VISTA improves robustness and generalization in deep learning by enforcing trajectory consistency through validation-informed expert anchors and coverage-weighted self-distillation.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
VISTA: Validation-Informed Trajectory Adaptation via Self-Distillation
VISTA improves robustness and generalization in deep learning by enforcing trajectory consistency through validation-informed expert anchors and coverage-weighted self-distillation.