Matt Thomson

According to our database, Matt Thomson authored at least 25 papers between 2019 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Fail Fast, or Ask: Mitigating the Deficiencies of Reasoning LLMs with Human-in-the-Loop Systems Engineering.

Michael J. Zellinger, Matt Thomson

CoRR, July, 2025

Economic Evaluation of LLMs.

Michael J. Zellinger, Matt Thomson

CoRR, July, 2025

Cost-Saving LLM Cascades with Early Abstention.

Michael J. Zellinger, Rex Liu, Matt Thomson

CoRR, February, 2025

Rational Tuning of LLM Cascades via Probabilistic Modeling.

Michael J. Zellinger, Matt Thomson

Trans. Mach. Learn. Res., 2025

2024

Engineering flexible machine learning systems by traversing functionally invariant paths.

Guruprasad Raghavan, Bahey Tharwat, Surya Narayanan Hari, Dhruvil Satani, Rex Liu, Matt Thomson

Nat. Mac. Intell., 2024

Automated construction of cognitive maps with visual predictive coding.

James Gornet, Matt Thomson

Nat. Mac. Intell., 2024

Efficiently Deploying LLMs with Controlled Risk.

Michael J. Zellinger, Matt Thomson

CoRR, 2024

Prompt Baking.

Aman Bhargava, Cameron Witkowski, Alexander Detkov, Matt Thomson

CoRR, 2024

Leveraging Open-Source Large Language Models for encoding Social Determinants of Health using an Intelligent Router.

Akul Goel, Surya Narayanan Hari, Belinda Waltman, Matt Thomson

CoRR, 2024

2023

Herd: Using multiple, smaller LLMs to match the performances of proprietary, large LLMs via an intelligent composer.

Surya Narayanan Hari, Matt Thomson

CoRR, 2023

What's the Magic Word? A Control Theory of LLM Prompting.

Aman Bhargava, Cameron Witkowski, Manav Shah, Matt Thomson

CoRR, 2023

Tryage: Real-time, intelligent Routing of User Prompts to Large Language Models.

Surya Narayanan Hari, Matt Thomson

CoRR, 2023

Automated mapping of virtual environments with visual predictive coding.

James Gornet, Matt Thomson

CoRR, 2023

2022

Minimal gene set discovery in single-cell mRNA-seq datasets with ActiveSVM.

Xiaoqiao Chen, Sisi Chen, Matt Thomson

Nat. Comput. Sci., 2022

Generating counterfactual explanations of tumor spatial proteomes to discover effective, combinatorial therapies that enhance cancer immunotherapy.

Zitong Jerry Wang, Matt Thomson

CoRR, 2022

Engineering flexible machine learning systems by traversing functionally invariant paths in weight space.

Guruprasad Raghavan, Matt Thomson

CoRR, 2022

Connectedness of loss landscapes via the lens of Morse theory.

Danil Akhtiamov, Matt Thomson

Proceedings of the NeurIPS Workshop on Symmetry and Geometry in Neural Representations, 2022

2021

CloudPred: Predicting Patient Phenotypes From Single-cell RNA-seq.

Bryan He, Matthew Thomson, Meena Subramaniam, Richard Perez, Chun Jimmie Ye, James Zou

CoRR, 2021

Active feature selection discovers minimal gene-sets for classifying cell-types and disease states in single-cell mRNA-seq data.

Xiaoqiao Chen, Sisi Chen, Matt Thomson

CoRR, 2021

Solving hybrid machine learning tasks by traversing weight space geodesics.

Guruprasad Raghavan, Matt Thomson

CoRR, 2021

Reinforcement Learning reveals fundamental limits on the mixing of active particles.

Dominik Schildknecht, Anastasia N. Popova, Jack Stellwagen, Matt Thomson

CoRR, 2021

2020

Sparsifying networks by traversing Geodesics.

Guruprasad Raghavan, Matt Thomson

CoRR, 2020

Self-organization of multi-layer spiking neural networks.

Guruprasad Raghavan, Cong Lin, Matt Thomson

CoRR, 2020

Geometric algorithms for predicting resilience and recovering damage in neural networks.

Guruprasad Raghavan, Jiayi Li, Matt Thomson

CoRR, 2020

2019

Neural networks grown and self-organized by noise.

Guruprasad Raghavan, Matt Thomson

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019