About me

Hi! My name is Carl Edwards, and I’m from Knoxville, Tennessee. I’m a PhD student in computer science at the University of Illinois at Urbana-Champaign where I’m advised by Professor Heng Ji. I completed my bachelor’s degree at the University of Tennessee, Knoxville in May 2020 where I majored in CS and math. Generally, I’m interested in models that can generalize well on multiple tasks and which learn from multiple contrasting yet complementary domains of data. Specifically, I’m interested in leveraging multiple modalities and domains of data centered around language. My research interests cover information extraction, information retrieval, natural language processing, representation learning, text mining, transfer learning, and multi-task learning. In particular, I’m interested in applying these tools to scientific texts to accelerate scientific discovery; I’m currently working on projects related to chemistry literature in association with the Molecule Maker Lab Institute, which provides an exciting testbed.

In the past, I’ve had the opportunity to work on a variety of exciting research projects!


See my (possibly outdated) resume attached here.


University of Illinois

I’ve been working with the Molecule Maker Lab Institute on integrating molecule and text information. A paper from this work, Text2Mol, was published at EMNLP2021.

Text2Mol Task

Text2Mol Examples

Here is the poster.


Carnegie Mellon University

During summer 2019, I worked at CMU as a Robotics Institute Summer Scholar. I conducted research in the Auton Lab with Prof. Artur Dubrawski working on detecting organizations in online escort advertisements. I used several similarity measures using tools like fastText word embeddings, face recognition, and others.


University of Zurich

During Fall 2018, I studied abroad at the University of Zurich in Zurich, Switzerland. While I was there, I worked on creating joint embeddings between images and knowledge graphs. My project report is here.


Oak Ridge National Lab

I interned at ORNL during the summers of 2017 and 2018 through the HERE and DOE SULI programs respectively. I worked on optimizing phase values in continuous subarrayed radar arrays using metaheuristic techniques like genetic algorithms and simulated annealing.

Optimized radar array. Note the cyclic behavior of the phase values.

University of Tennessee

From fall 2016 to spring 2018, I worked as an undergraduate research assistant. I worked on molecular dynamics simulations and data analysis. I also performed Brownian dynamics simulations of flowing polymer solutions, and I extracted solution properties from the resulting data.

Photo Photo


Publications, Posters, etc.


Text2Mol: Cross-Modal Molecular Retrieval with Natural Language Queries

Carl Edwards, ChengXiang Zhai, and Heng Ji
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2021.

[pdf] [video - on underline] [code]

Team Skeletor at Touché 2021: Argument Retrieval and Visualization for Controversial Questions

Kevin Ros*, Carl Edwards*, Heng Ji, and ChengXiang Zhai
CLEF (Working Notes) 2441-2454. 2021.
[pdf] [video] [code]

* - equal contribution

Journal Article

In-plane and out-of-plane rotational motion of individual chain molecules in steady shear flow of polymer melts and solutions, C.N. Edwards, M.H. Nafar Sefiddashti, B.J. Edwards, and B. Khomami, J. Mol. Graph. Model., 81, 184-196 (2018).

Using Similarity Measures to Detect Organizations in Online Escort Advertisements, C. Edwards, A. Wertz, and A. Dubrawski, Robotics Institute Summer Scholar’ Working Papers Journal, 7, 43-49 (2019).


Out-of-plane rotational motion in shear flow of polymer melts and solutions, M.H. Nafar Sefiddashti, C.N. Edwards, B.J. Edwards, and B. Khomami, The Society of Rheology 89th Annual Meeting, Denver, CO, October 8-12, 2017.


Edwards C., Zhai CX., Ji H., Text2Mol: Cross-modal Molecular Retrieval with Natural Language Queries. Poster presented at: Molecule Maker Lab Institute Retreat 2021; 2021 August 2; Urbana, IL

Edwards C.N., Wertz A., Dubrawski A.W., Using Similarity Measures to Detect Organizations in Online Escort Advertisements. Poster presented at: RISS 2019 Poster Session; 2019 August 14; Pittsburgh, PA.

Edwards C.N., Daniel B., Beam Broadening of Subarrayed Radar Arrays Utilizing Various Global Optimization Techniques. Poster presented at: ORNL 2018 Undergraduate Research Poster Session; 2018 August 1; Oak Ridge, TN


Daniel, Barry, Carl Edwards, and Adam Anderson. “Phase-Only Beam Broadening of Contiguous Uniform Subarrayed Arrays Utilizing Three Metaheuristic Global Optimization Techniques.” arXiv preprint arXiv:2009.06123 (2020).

Selected Awards and Honors

Saburo Muroga Endowed Fellowship

Goldwater Scholar

Min Kao Scholar (2018, 2019)


Outstanding Computer Science Junior 2018 (Sole recipient)


Recognition of Pi Mu Epsilon Tennessee Delta Chapter


See other awards on my resume above.


NSF Molecule Maker Laboratory Institute – Student and Postdoc Council Educational & Outreach Activities Chair

Presentations to High School Students:

o Summer 2019: Presentation on “Detecting Human Trafficking Organizations” with AI4All@CMU

o April 2021: Illinois CS Sail course on “Learning Word Representations


ACL-IJCNLP Demo Track 2021

Some Random Projects

Multimodal Molecule Reaction Prediction from Knowledge Graph of Reactions [Proposal] [Report]

Optimization of a hybrid electric vehicle energy management control parameters by metaheuristic methods

Avoiding Catastrophic Forgetting in AI Safety Gridworld

Fashion MNIST Investigation

High School Projects

Neural networks looking for food


old Minecraft Bukkit mod (pre 1.7)

Some fun activities I’ve done

UTK Machine Learning Club

Photo Photo

Art competition entry using neural style transfer.



Martial Arts

Classical Singing


Governor’s School for Computational Physics


FIRST Robotics





Volunteering at Salvation Army food pantry


Volunteering at Ijams River Rescue


Volunteering at KARM

Volunteering after Gatlinburg fires to sort donations