conftrace_

logits distillation

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

knowledge distillation (2) model compression (2) kendall's tau (1) inter-class information (1) gradient scaling (1) teacher logit (1) large language model (1) student model (1) student network (1) ranking loss (1)

Papers

BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation COLING 2025 Enhancing Logits Distillation with Plug&Play Kendall’s $τ$ Ranking Loss ICML 2025 Grouped Knowledge Distillation for Deep Face Recognition AAAI 2023