activity
20002026
most citedProbabilistic Modeling with Matrix Product States

30 citations · 115 across the 21 of their papers we have counts for

collaborators

21 papers

cs.LO2026★ 1 cited

A calculus of types in Isbell nuclei

Juan Luis Gastaldi, Samantha Jarvis, Thomas Seiller +1

We identify two constructions from different mathematical traditions. In linear logic and realisability, logical types are generated rather than fixed in advance: one begins with a…

math.AG2026★ 1 cited

Projective metric geometry of tropical nuclei: gap matrices, event loci, and order chambers

Juan Luis Gastaldi, Samantha Jarvis, Thomas Seiller +1

The tropical row span and column span of a real matrix are, from the polyhedral point of view, different objects living in different ambient spaces. These polytopes are known to be…

cs.CL2024

From Language Models over Tokens to Language Models over Characters

Tim Vieira, Ben LeBrun, Mario Giulianelli +5

Modern language models are internally -- and mathematically -- distributions over strings rather than strings, posing numerous challenges for programm…

cs.CL2024★ 1 cited

The Foundations of Tokenization: Statistical and Computational Concerns

Juan Luis Gastaldi, John Terilla, Luca Malagutti +3

Tokenization - the practice of converting strings of characters from an alphabet into sequences of tokens over a vocabulary - is a critical step in the NLP pipeline. The use of tok…

math.CT2021

An enriched category theory of language: from syntax to semantics

Tai-Danae Bradley, John Terilla, Yiannis Vlassopoulos

State of the art language models return a natural language text continuation from any piece of input text. This ability to generate coherent text extensions implies significant sop…

cs.LG2020★ 5 cited

Tensor Networks for Probabilistic Sequence Modeling

Jacob Miller, Guillaume Rabusseau, John Terilla

Tensor networks are a powerful modeling framework developed for computational many-body physics, which have only recently been applied within machine learning. In this work we util…