DEPARTMENT OF COMPUTER SCIENCE — INSTITUTE OF TECHNOLOGY

Dr. Aria Voss

Professor of Artificial Intelligence & Distributed Systems

Building machines that reason under uncertainty, and the students who'll out‑build me. Eighteen years in front of a chalkboard, fourteen in front of a GPU cluster.

scroll
01

About

AV

Dr. Voss leads the Reasoning Systems Lab, where her team studies how learning systems can make trustworthy decisions when the data runs out. Before joining the faculty, she spent four years building inference infrastructure in industry — work she now mines for examples in every lecture.

She believes the best research questions are the ones a curious undergraduate asks by accident, and she keeps a running notebook of them on her office door.

0 Years Teaching
0 Publications
0 Graduate Students Mentored
0 Patents Filed
02

Research Areas

PROBABILISTIC ML

Reasoning Under Uncertainty

Bayesian deep learning methods that know when to say "I don't know" — applied to medical triage and autonomous navigation.

View related papers ↓
DISTRIBUTED SYSTEMS

Federated Inference

Training and serving models across thousands of edge devices without ever centralizing raw data.

View related papers ↓
HUMAN-AI INTERACTION

Calibrated Trust

How people build (and lose) trust in AI recommendations, and how interfaces can communicate model confidence honestly.

View related papers ↓
SYSTEMS FOR ML

Low-Resource Training

Making model training accessible on modest hardware for labs and classrooms without datacenter budgets.

View related papers ↓
03

Selected Publications

2026

Calibrated Abstention in Clinical Triage Models

Voss, A., Renner, T., Okafor, L. — Journal of Machine Learning Research

We introduce a method for learned models to defer to clinicians when predictive confidence falls below a task-specific threshold, reducing false-confidence errors by 41% on three hospital triage datasets without sacrificing throughput.

2025

Federated Inference at the Edge: A Three-Year Field Study

Voss, A., Park, S. — ACM Transactions on Computer Systems

A longitudinal deployment across 4,000 edge devices shows that periodic re-synchronization, rather than continuous federated updates, yields better accuracy-per-watt for resource-constrained classrooms and clinics.

2025

What Makes an Explanation Feel Honest?

Voss, A., Whitfield, R. — CHI Conference on Human Factors in Computing

A user study of 312 participants finds that explanation length matters less than whether the system discloses its own uncertainty — a result we use to redesign confidence indicators in three production systems.

2024

Training Transformers on a Single Classroom GPU

Voss, A., Imani, D. — NeurIPS Workshop on Resource-Efficient ML

A curriculum of gradient checkpointing, sparse attention, and staged distillation that brings transformer pretraining within reach of a single consumer GPU, with full lab materials released for instructors.

2023

Bayesian Navigation Under Sensor Drift

Voss, A., Castellanos, M., Renner, T. — IEEE Transactions on Robotics

A drift-aware particle filter that maintains calibrated uncertainty estimates over multi-hour autonomous navigation tasks, tested on six campus delivery robots.

04

Courses Taught

CS 4710

Probabilistic Machine Learning

Graduate seminar on Bayesian inference, variational methods, and uncertainty quantification in deep networks.

FALL · SPRING
CS 3300

Distributed Systems

Core undergraduate course covering consensus, replication, and the federated systems used throughout the lab's research.

FALL
CS 1100

Introduction to Computing

First-year gateway course — the one Dr. Voss has refused to stop teaching for eighteen years running.

FALL · SPRING
CS 5900

Doctoral Research Seminar

Weekly seminar for PhD candidates presenting work-in-progress to the Reasoning Systems Lab and invited critics.

YEAR-ROUND
05

Honors & Service

2026

Distinguished University Teaching Award

Awarded by the Institute's Faculty Senate for sustained excellence in undergraduate instruction.

2024

ACM Senior Member

Recognized for sustained contributions to distributed machine learning systems.

2022

NSF CAREER Award

Five-year grant supporting research into calibrated uncertainty for safety-critical AI systems.

2020

Department Chair, Graduate Admissions

Redesigned the department's graduate admissions process to weight research potential over standardized testing.

2017

Best Paper Award, IEEE ICRA

For early work on drift-aware uncertainty estimation in mobile robotics.

06

Get in Touch

Office hours are real and held weekly — students, collaborators, and curious sophomores are equally welcome.

Email
a.voss@university.edu
Office
Turing Hall, Room 412
Office Hours
Tue / Thu, 2:00 – 4:00 PM
Lab
Reasoning Systems Lab, Turing Hall B-Wing