2 papers
cs.LG2026
Kan Extension Transformers: A Categorical Unification of Attention, Diffusion, and Predict-Detach Self-Conditioning
Sridhar Mahadevan
We propose Kan Extension Transformers (KETs) as a categorical design language for a diverse group of Transformer implementations. A layer can be viewed generally as a weighted stru…
cs.AI2025
Topos Theory for Generative AI and LLMs
Sridhar Mahadevan
We propose the design of novel categorical generative AI architectures (GAIAs) using topos theory, a type of category that is ``set-like": a topos has all (co)limits, is Cartesian…