Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation

22 December 2023

Xue Liu

Papers citing "Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation"

3 / 3 papers shown

Title
MoKD: Multi-Task Optimization for Knowledge Distillation Zeeshan Hayder A. Cheraghian Lars Petersson Mehrtash Harandi VLM 54 0 0 13 May 2025
VRM: Knowledge Distillation via Virtual Relation Matching W. Zhang Fei Xie Weidong Cai Chao Ma 76 0 0 28 Feb 2025
Bilevel Programming for Hyperparameter Optimization and Meta-Learning Luca Franceschi P. Frasconi Saverio Salzo Riccardo Grazzi Massimiliano Pontil 110 716 0 13 Jun 2018