Saved in:
Bibliographic Details
Main Author: Mahadevan, Sridhar
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.27259
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910261268447232
author Mahadevan, Sridhar
author_facet Mahadevan, Sridhar
contents We propose Kan Extension Transformers (KETs) as a unifying categorical framework for a diverse group of Transformer implementations. The core claim is that a Transformer layer can be viewed as a weighted structured extension operator: standard attention is the singleton-neighborhood case, Geometric Transformer style incidence mixing is a sparse edge-restricted case, and KET is the higher-order simplicial case. This lens also clarifies a bridge to diffusion-style completion. When the extension operator acts on detached predictive carriers instead of teacher-forced hidden states, it becomes a valid self-conditioning mechanism that exposes noncausal structure without leaking gold future tokens. We include a comprehensive experimental validation of 12 different Transformer implementations varying across strict-causal and predict-detach regimes on Penn Treebank, WikiText-2, and WikiText-103. In the strict-causal setting, quadratic KET is the strongest model among the compared causal architectures on WikiText-2 and WikiText-103. Across all datasets, however, the largest gains come from the predict-detach regime rather than from changing the neighborhood family alone.
format Preprint
id arxiv_https___arxiv_org_abs_2605_27259
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Kan Extension Transformers: A Categorical Unification of Attention, Diffusion, and Predict-Detach Self-Conditioning
Mahadevan, Sridhar
Machine Learning
We propose Kan Extension Transformers (KETs) as a unifying categorical framework for a diverse group of Transformer implementations. The core claim is that a Transformer layer can be viewed as a weighted structured extension operator: standard attention is the singleton-neighborhood case, Geometric Transformer style incidence mixing is a sparse edge-restricted case, and KET is the higher-order simplicial case. This lens also clarifies a bridge to diffusion-style completion. When the extension operator acts on detached predictive carriers instead of teacher-forced hidden states, it becomes a valid self-conditioning mechanism that exposes noncausal structure without leaking gold future tokens. We include a comprehensive experimental validation of 12 different Transformer implementations varying across strict-causal and predict-detach regimes on Penn Treebank, WikiText-2, and WikiText-103. In the strict-causal setting, quadratic KET is the strongest model among the compared causal architectures on WikiText-2 and WikiText-103. Across all datasets, however, the largest gains come from the predict-detach regime rather than from changing the neighborhood family alone.
title Kan Extension Transformers: A Categorical Unification of Attention, Diffusion, and Predict-Detach Self-Conditioning
topic Machine Learning
url https://arxiv.org/abs/2605.27259