Vislang Lab
Under the advice of Dr. Vicente Ordóñez-Román
Verónica Flores
B.S. Candidate, Computer Science, and Engineering
Double Minoring in Mathematics and Political Science
Department of Computer Science and Engineering
Departments of Mathematics and Political Science
Santa Clara University
vflores@scu.edu
About Me
My name is Verónica Flores and I am a rising junior majoring in Computer Science & Engineering from Santa Clara University in California. I am also double minoring in Mathematics and Political Science and plan to graduate in Spring 2025. In the past, I have researched at Oregon State University under the advice of Dr.Stephen Ramsey in the ramseylab through the Department of Biological Science in the School of Electrical Engineering and Computer Science. In 2020, I was an Oregon and SW Washington Affiliate Award Winner of the NCWIT Award for Aspirations in Computing. Moreover, this Summer, I am researching in the Vision, Language, and Learning Lab at Rice University through the CRA-WP DREU Program for the second summer in a row. You may access my website from last Summer here. My host is again Associate Professor Vicente Ordóñez-Román from the Department of Computer Science at Rice University.
About My Mentor
Professor Vicente Ordóñez-Román’s official bio lies in his lab’s website.
Dr. Vicente Ordóñez-Román is an Associate Professor in Department of Computer Science at Rice University where he leads the Vision, Learning, and Language Lab, and is a Amazon Visiting Academic at Amazon Alexa AI. From 2016-2021 he was an Assistant Professor in the Department of Computer Science at the University of Virginia. In the past, he has also been visiting professor at Adobe Research and visiting researcher at the Allen Institute for Artificial Intelligence (AI2). He received his PhD in Computer Science at the University of North Carolina at Chapel Hill in 2015 advised by Prof. Tamara L. Berg, an MS in Computer Science at Stony Brook University (SUNY) and an engineering degree at the Escuela Superior Politécnica del Litoral in Ecuador. He’s a recipient of a Best -Long- Paper Award at the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP), and the Best Paper Marr Prize at the 2013 International Conference in Computer Vision (ICCV). He has also received an NSF CAREER Award, an IBM Faculty Award, a Google Faculty Research Award, and a Facebook Research Award. Here is a link to an official bio, and his curriculum vitae.
About My Project
This summer, I am continuing my research with vision and language models used in machine learning. Moreover, these models use natural language processing and computer vision in order to identify various images and text outputs. Specifically, my project will explore societal biases in large-scale models trained with contrastive objects.
The machine learning model we will be using is the CLIP Model, which is trained via natural language supervision. The CLIP model uses a Byte-Pair encoding tokenizer and is a dual-stream Vision Transformer (ViT). For my project we will be expanding on my work last Summer which you can access here. Last Summer I created three different benchmarks which tested the CLIP model, using the Politician dataset I constructed, in its gender and political affiliation bias. This Summer, I plan to delve into the base benchmark and run more tests that include other public figures aside from politicians, such as athletes, artists, and actors. I hope to uncover a more clear gender bias and implement mitigations.
My final report will be updated at the end of the Summer. My Final Report
About the DREU Progam
The Distributed Research Experiences for Undergraduates (DREU) program aims to increase the diversity of computer science/engineering graduate students by matching students with faculty mentors at institutions across the United States for a 10-week, fully funded summer research experience. DREU is organized by the Computing Research Association’s Committee on Widening Participation in Computing Research (CRA-WP) and supported by the National Science Foundation.
My Blog
Check my blog for weekly updates here!