3 papers
cs.LG2026
Deep Neural Networks with Ordinal Loss for Medical Applications
Tal Dvora, Rotem Haba, Gonen Singer
In many prediction problems in medical applications, target labels exhibit an inherent ordinal structure, where class ordering reflects clinically meaningful severity levels. The c…
cs.LG2026
Complementary Attention Head Pruning for Efficient Transformers
Yaniv Livertovsky, Shahar Somin, Gonen Singer
The remarkable success of Transformer-based models in natural language processing stems from architectural scaling, which leads to a large number of parameters and hinders deployme…
cs.CV2026
CoSeP: Complementary Separability Pruning via Class-Separability Clustering
David Levin, Gonen Singer
Neural network pruning aims to compress models for efficient deployment, yet two fundamental challenges remain. First, many methods rely on per-component importance scores, selecti…