3 papers
cs.LG2026
A Unified Framework for Quantized and Continuous Strong Lottery Tickets
Aakash Kumar, Emanuele Natale
The Strong Lottery Ticket Hypothesis (SLTH) asserts that sufficiently overparameterized, randomly initialized neural networks contain sparse subnetworks that, even without any trai…
cs.LG2026
Compositional Generalization in Autoregressive Models via Logit Composition
Aakash Kumar, Maria Sofia Bucarelli, Emanuele Natale
Composing autoregressive models remains a core challenge in understanding how large language models can combine behaviors or skills learned across tasks. We introduce a new and pri…
cs.LG2026
Beyond Fixed Points: Superpolynomial Capacity of Asymmetric Hopfield Networks
Aakash Kumar, Anatoly Khina, Frederik Mallmann-Trenn +1
Classical Hopfield networks are limited to static patterns due to symmetric weights, whereas asymmetric networks can encode temporal sequences via limit-cycle attractors. Achieving…