Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Feature Evolution and Migration during Vision Transformer Training
Joonas Järve, Halil Ibrahim Aysel, Tarun Khajuria +1
We present a novel view on feature evolution in Vision Transformers (ViTs) by visualizing the training process over two dimensions -- network depth (layer) and training time (epoch…
cs.AI2026
How Uncertainty Estimation Scales with Sampling in Reasoning Models
Maksym Del, Markus Kängsepp, Marharyta Domnich +4
Uncertainty estimation is critical for deploying reasoning language models, yet remains poorly understood under extended chain-of-thought reasoning. We study parallel sampling as a…