Picture for Matt Thomson

Matt Thomson

Efficiently Deploying LLMs with Controlled Risk

Add code
Oct 03, 2024
Viaarxiv icon

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

Add code
May 30, 2024
Viaarxiv icon

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

Add code
Oct 30, 2023
Viaarxiv icon

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

Add code
Oct 10, 2023
Viaarxiv icon

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

Add code
Aug 23, 2023
Viaarxiv icon

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

Add code
Nov 08, 2022
Viaarxiv icon

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

Add code
May 09, 2022
Figure 1 for Engineering flexible machine learning systems by traversing functionally invariant paths in weight space
Figure 2 for Engineering flexible machine learning systems by traversing functionally invariant paths in weight space
Figure 3 for Engineering flexible machine learning systems by traversing functionally invariant paths in weight space
Figure 4 for Engineering flexible machine learning systems by traversing functionally invariant paths in weight space
Viaarxiv icon

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

Add code
Jun 15, 2021
Viaarxiv icon

Solving hybrid machine learning tasks by traversing weight space geodesics

Add code
Jun 05, 2021
Figure 1 for Solving hybrid machine learning tasks by traversing weight space geodesics
Figure 2 for Solving hybrid machine learning tasks by traversing weight space geodesics
Figure 3 for Solving hybrid machine learning tasks by traversing weight space geodesics
Figure 4 for Solving hybrid machine learning tasks by traversing weight space geodesics
Viaarxiv icon

Reinforcement Learning reveals fundamental limits on the mixing of active particles

Add code
May 28, 2021
Figure 1 for Reinforcement Learning reveals fundamental limits on the mixing of active particles
Figure 2 for Reinforcement Learning reveals fundamental limits on the mixing of active particles
Figure 3 for Reinforcement Learning reveals fundamental limits on the mixing of active particles
Figure 4 for Reinforcement Learning reveals fundamental limits on the mixing of active particles
Viaarxiv icon