CIST uses per-sample adaptive temperatures for both teacher and student in knowledge distillation to ensure consistent entropy in soft labels and reports gains on vision and language tasks.
Dynamic temperature knowledge distillation.arXiv preprint arXiv:2404.12711,
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
-
Consistently Informative Soft-Label Temperature for Knowledge Distillation
CIST uses per-sample adaptive temperatures for both teacher and student in knowledge distillation to ensure consistent entropy in soft labels and reports gains on vision and language tasks.