collaborators

5 papers

cs.LG2026

Training Crossroads for Recurrent Vision Transformers: Recurrence, Neural ODEs, and Deep Supervision

Grzegorz Gruszczynski, Pawel Olszowiec, Michal Byra +2

Vision Transformers (ViTs) achieve strong image-recognition performance, but their parameter count grows linearly with depth when each block is independently parameterized. Single-…

cs.LG2026

t-gems: text-guided exit modules for decreasing clip image encoder

Alberto Presta, Grzegorz Stefanski, Michal Byra +1

Multimodal deep neural networks enhance deep comprehension by integrating diverse data modalities. Data from different modalities are typically projected into a shared latent space…

cs.CV2026

bViT: Investigating Single-Block Recurrence in Vision Transformers for Image Recognition

Michal Byra, Pawel Olszowiec, Grzegorz Stefanski +2

Vision Transformers (ViTs) are built by stacking independently parameterized blocks, but it remains unclear how much of this depth requires layer specific transformations and how m…

cs.AI2026

Routing the Lottery: Adaptive Subnetworks for Heterogeneous Data

Grzegorz Stefanski, Alberto Presta, Michal Byra

In pruning, the Lottery Ticket Hypothesis posits that large networks contain sparse subnetworks, or winning tickets, that can be trained in isolation to match the performance of th…

cs.LG2024

SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model

Grzegorz Stefański, Paweł Daniluk, Artur Szumaczuk +1

Consumer electronics used to follow the miniaturization trend described by Moore's Law. Despite increased processing power in Microcontroller Units (MCUs), MCUs used in the smalles…