Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Traversing the solution space of neural networks with Hessian Null Space Continuation
Ann Huang, Mitchell Ostrow, Zhouyang Lu +3
On a single task, deep networks can learn many solutions, depending on their optimizer, training data, architecture, and hyperparameters. Many of these solutions are mode-connected…
cs.LG2026
Self-Attention at Constant Cost per Token via Symmetry-Aware Taylor Approximation
Franz A. Heinsen, Leo Kozachkov
The most widely used artificial intelligence (AI) models today are Transformers employing self-attention. In its standard form, self-attention incurs costs that increase with conte…