2 papers
cs.LG2026
Feature Superposition in Neural Networks: From Theory to Practice
Dai Shi, Xiaoyu Li, Andi Han +1
Superposition refers to neural networks representing more features than they have dimensions. It offers a possible explanation for polysemantic neurons and motivates methods for re…
cs.CL2026
When the Canonical Completion Is Wrong: Formalizing and Measuring the Jump in Large Language Models
Dai Shi, Xiaoyu Li, José Miguel Hernández-Lobato
Whether large language models (LLMs) can perform the abductive leap from evidence to a new system of axioms, commonly referred to as a jump, has recently attracted considerable deb…