3 papers
cs.LG2026
REDistill: Robust Estimator Distillation for Balancing Robustness and Efficiency
Ondrej Tybl, Lukas Neumann
Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student by aligning their predictive distributions. However, conventional KD formulations -…
cs.CV2025
Universal Neural Architecture Space: Covering ConvNets, Transformers and Everything in Between
OndÅej Týbl, Lukáš Neumann
We introduce Universal Neural Architecture Space (UniNAS), a generic search space for neural architecture search (NAS) which unifies convolutional networks, transformers, and their…
cs.CV2025
Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights
OndÅej Týbl, Lukáš Neumann
Deep learning has revolutionized computer vision, but it achieved its tremendous success using deep network architectures which are mostly hand-crafted and therefore likely subopti…