3 papers
cs.LG2026
Same path, different: a mechanistic comparison of looped and stacked transformer encoders on 12-lead ECG
Pawel Olszowiec, Michal Byra, Grzegorz Gruszczynski +2
Recurrent Transformers reusing their weights rather than stacking distinct layers are becoming widely adopted due to their parameter efficiency [1,2,3]. However, the exact repr…
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.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…