Weak-to-strong knowledge distillation applied early and then turned off accelerates convergence to target performance in visual learning tasks by factors of 1.7-4.8x.
Title resolution pending
2 Pith papers cite this work, alongside 116 external citations. Polarity classification is still indexing.
2
Pith papers citing it
116
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Rec-Distill is an industrial distillation pipeline that transfers substantial performance from large-scale recommendation models to efficient students, reporting over 60% transferability and measurable business gains.
citing papers explorer
-
Weak-to-Strong Knowledge Distillation Accelerates Visual Learning
Weak-to-strong knowledge distillation applied early and then turned off accelerates convergence to target performance in visual learning tasks by factors of 1.7-4.8x.
-
Rec-Distill: An Industrial Distillation Pipeline for Large-Scale Recommendation Models
Rec-Distill is an industrial distillation pipeline that transfers substantial performance from large-scale recommendation models to efficient students, reporting over 60% transferability and measurable business gains.