conftrace_

teacher logit

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

knowledge distillation (2) logits-based fine-tuning (1) token-level dependencies (1) gradient scaling (1) logits distillation (1) kendall's tau (1) inter-class information (1) binary network (1) large language model (1) linguistic diversity (1)

Papers

Enhancing Logits Distillation with Plug&Play Kendall’s $τ$ Ranking Loss ICML 2025 Logits-Based Finetuning EMNLP 2025 Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study ICLR 2021