collaborators

6 papers

cs.AI2026

Interpreting Language Model Hidden States at Scale

Jordan Pettyjohn, Mansi Sakarvadia, Nathaniel Hudson +3

Lens methods interpret large language models (LLMs) by mapping intermediate activations to the output vocabulary, revealing how next-token predictions develop through the network.…

cs.LG2025

Steering an Active Learning Workflow Towards Novel Materials Discovery via Queue Prioritization

Marcus Schwarting, Logan Ward, Nathaniel Hudson +5

Generative AI poses both opportunities and risks for solving inverse design problems in the sciences. Generative tools provide the ability to expand and refine a search space auton…

cs.DC2025

Addressing Reproducibility Challenges in HPC with Continuous Integration

Valérie Hayot-Sasson, Nathaniel Hudson, André Bauer +3

The high-performance computing (HPC) community has adopted incentive structures to motivate reproducible research, with major conferences awarding badges to papers that meet reprod…

cs.CE2025

AERO: An autonomous platform for continuous research

Valérie Hayot-Sasson, Abby Stevens, Nicholson Collier +10

The COVID-19 pandemic highlighted the need for new data infrastructure, as epidemiologists and public health workers raced to harness rapidly evolving data, analytics, and infrastr…

cs.LG2025

Topology-Aware Knowledge Propagation in Decentralized Learning

Mansi Sakarvadia, Nathaniel Hudson, Tian Li +2

Decentralized learning enables collaborative training of models across naturally distributed data without centralized coordination or maintenance of a global model. Instead, device…

cs.DC2025

MOFA: Discovering Materials for Carbon Capture with a GenAI- and Simulation-Based Workflow

Xiaoli Yan, Nathaniel Hudson, Hyun Park +15

We present MOFA, an open-source generative AI (GenAI) plus simulation workflow for high-throughput generation of metal-organic frameworks (MOFs) on large-scale high-performance com…