no code implementations • 19 Mar 2025 • Michael Robinson, Sourya Dey, Taisa Kushner
This article presents a general and flexible method for prompting a large language model (LLM) to reveal its (hidden) token input embedding up to homeomorphism.
no code implementations • 11 Oct 2024 • Michael Robinson, Sourya Dey, Shauna Sweet
Large language models encode the correlational structure present in natural language by fitting segments of utterances (tokens) into a high dimensional ambient latent space upon which the models then operate.
1 code implementation • 30 Jan 2024 • Steve Huntsman, Michael Robinson, Ludmilla Huntsman
We demonstrate that large language models can produce reasonable numerical ratings of the logical consistency of claims.
no code implementations • 9 Feb 2023 • Michael Robinson, Tate Altman, Denley Lam, Letitia W. Li
The pattern of messages can be used as the signature of a particular kind of behavior, with the understanding that some messages are likely to co-occur, while others are not.
no code implementations • 19 May 2022 • Michael Robinson, Zander Memon
A simple theoretical model is developed that yields a precise, yet qualitative, description of the space of echoes.
no code implementations • 28 Jun 2016 • Michael Robinson
This article presents a two-stage topological algorithm for recovering an estimate of a quasiperiodic function from a set of noisy measurements.
1 code implementation • 15 Apr 2016 • Michael Robinson
Without referring to the models directly -- only that a model consists of spaces and maps between them -- the most readily apparent feature of a multi-model system is its topology.
Algebraic Topology 18F20, 46M20
1 code implementation • 4 Mar 2016 • Michael Robinson
A sensor integration framework should be sufficiently general to accurately represent all information sources, and also be able to summarize information in a faithful way that emphasizes important, actionable information.
Algebraic Topology 55N30