Francisco
Romero

General Information

Email:
faromero@gatech.edu
Phone:
9072290327
Location - Building:
KACB
Location - Room:
3142
Roles:
Professor (any rank)
Primary Unit:
College of Computing
Website URL
http://www.franciscoaromero.com

Details

Degrees with subject and Postdoc Experience:
Degree Type
B.S.
Subject
Electrical Engineering-Computer Engineering
Year
2015
Institution
University of Southern California
Location
Los Angeles, CA
Degree Type
M.S.
Subject
Electrical Engineering
Year
2017
Institution
Stanford University
Location
Stanford, CA
Degree Type
Ph.D.
Subject
Electrical Engineering
Year
2023
Institution
Stanford University
Location
Stanford, CA
Statement of Research Interests:

My research focuses on systems for machine learning and spans across the fields of computer systems, databases, and applied artificial intelligence. My recent work has focused on machine learning inference and video analytics, with a particular interest in edge/wearable-cloud systems.

Statement of Teaching Interests:

My teaching interests are in undergraduate and graduate courses in computer systems and architecture, databases and data systems, edge computing, and practical applications that touch on all of these such as large scale and real-time video analytics.

Selection of recent research, scholarly, and creative activities:

Kausar Patherya, Ashutosh Dhekne, and Francisco Romero. “Flash-Fusion: Enabling Expressive, Low-Latency Queries on IoT Sensor Streams with LLMs”. Pre-print. 2025.

Daniel Mendoza, Francisco Romero, and Caroline Trippel.“Model Selection for Latency-Critical Inference Serving”. European Conference on Computer Systems (EuroSys), Athens, Greece, 2024.

Francisco Romero*, Caleb Winston*, Johann Hauswald, Matei Zaharia, and Christos Kozyrakis. “Zelda: Video Analytics using Vision-Language Models”. Pre-print. 2024.

Francisco Romero, Johann Hauswald, Aditi Partap, Daniel Kang, Matei Zaharia, and Christos Kozyrakis.“Optimizing Video Analytics with Declarative Model Relationships”. Conference on Very Large Data Bases (VLDB), Vancouver, Canada, 2023.

Francisco Romero*, Daniel Kang*, Peter Bailis, Christos Kozyrakis, and Matei Zaharia. “VIVA: An End-to-End System for Interactive Video Analytics”. Conference on Innovative Data Systems Research (CIDR), Chaminade, CA, 2022.