Jul 2026
Optimizing knowledge distillation models for language models
The main result of this work is the development of a new compression method for CNNs based on geometrically controlled thinning of the CNN model, which can be applied to problems requiring real-time decision making as well as on mobile and embedded devices.
T. Tatarnikova, A. S. Raskopina
· Scientific and Technical Jou... · 0 citations