Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Sequential Group Composition: A Window into the Mechanics of Deep Learning
Giovanni Luca Marchetti, Daniel Kunin, Adele Myers +2
How do neural networks trained over sequences acquire the ability to perform structured operations, such as arithmetic, geometric, and algorithmic computation? To gain insight into…
cs.LG2026
Symmetry Breaking in Transformers for Efficient and Interpretable Training
Eva Silverstein, Daniel Kunin, Vasudev Shyam
The attention mechanism in its standard implementation contains extraneous rotational degrees of freedom that are carried through computation but do not affect model activations or…