conftrace_

distillation loss

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

glue benchmark (1) large language model (1) cross-architecture generalization (1) classifier weights scaling (1) bert distillation (1) adaptive distillation coefficients (1) high-resolution dataset (1) teacher model (1) synthetic sample (1) student model (1)

Papers

Large Scale Dataset Distillation with Domain Shift ICML 2024 Provable Contrastive Continual Learning ICML 2024 Cost-effective Distillation of Large Language Models ACL 2023 ScaIL: Classifier Weights Scaling for Class Incremental Learning WACV 2020