Author

Xiao-Yu Li

h-index 0 View on Semantic Scholar

We have 3 of 4 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

When the Canonical Completion Is Wrong: Formalizing and Measuring the Jump in Large Language Models

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 debate. A prominent position holds that LLMs are structurally incapable of such jumps, while recent studies challenge both its mechanism and em...

Dai Shi, Xiao-Yu Li, José Miguel Hernández-Lobato · 0 citations

#machine learning Review Sep 2026

Feature Superposition in Neural Networks: From Theory to Practice

Superposition refers to neural networks representing more features than they have dimensions. It offers a possible explanation for polysemantic neurons and motivates methods for recovering interpretable features from neural activations. Theoretical models typically start with a given set of input features and assumptio...

Dai Shi, Xiao-Yu Li, Andi Han et al. · 0 citations

#machine learning Preprint Aug 2026

When the Canonical Completion Is Wrong: Formalizing and Measuring the Jump in Large Language Models

A formal account of the jump is developed in four steps and measured, proving that jump instances are well-posed and establish a family theorem that certifies instances of unbounded difficulty without enumeration and further formalize when a jump is correct and how successive jumps compound.

Dai Shi, Xiao-Yu Li, José Miguel Hernández-Lobato · 0 citations