News

In her Ph.D. research in computer science, Xuxin Tang is focused on developing interactive systems where humans and large language models (LLMs) — often seen as “two black boxes” — can work together more effectively to support analytical tasks and writing, and enhance sensemaking. 

A real-world example of this is her work on designing visual workspaces that help users interact with LLMs for summarizing and analyzing large information sets. 

“Imagine a journalist researching a complex topic with hundreds of sources,” said Tang.  By using a visual workspace, they can organize, analyze, and explore information with the help of an LLM, which generates summaries, finds connections, and adapts based on the user’s evolving needs. This approach not only makes the analysis more efficient but also helps users retain oversight and fine-tune the AI’s contributions, ensuring that the final output aligns with their insights and goals.”

Tang, who earned a bachelor’s degree in engineering and a master of science from Wuhan University, China, is advised by Chris North at the Sanghani Center.

“The collaborative and interdisciplinary research environment at the center encourages innovation and creativity,” said Tang. “By bringing together students and faculty from diverse fields, being at the Sanghani center allows me to gain insights beyond my primary focus areas and approach my research in human-LLM collaboration and visual analytics from fresh perspectives.”

In October, Tang published and presented the paper, “Steering LLM Summarization with Visual Workspaces for Sensemaking” at the IEEE VIS 2024 workshop — NLVIZ: Exploring Research Opportunities for Natural Language, Text, and Data Visualization.

Tang’s attraction to his area of research grew from her background in machine learning and recommendation systems, where he saw both the incredible potential and the challenges of AI, she said. “I realized that while these models can process massive amounts of information and generate insights, they often operate as ‘black boxes,” limiting human oversight and understanding. This sparked my interest in finding ways to make AI more interpretable and collaborative.”

Projected to graduate in 2027, Tang said that she will pursue positions in both academia and industry to further advance her research.

Meng Lu is a Ph.D. student in computer science whose work focuses on complex planning with large language models (LLMs) to address intricate, data-driven challenges in real-world applications. Earlier this month, he was in Miami, Florida, where he and his advisor Xuan Wang presented “TriageAgent: Towards Better Multi-Agents Collaborations for Large Language Model-Based Clinical Triage” in main proceedings at the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP).

Another collaborator on the paper is Dennis Ren, assistant professor, Pediatric Emergency Medicine, Children’s National Hospital in Washington, D.C. 

“From the start, Professor Wang introduced me to several cutting-edge directions on LLMs, giving me a foundational understanding of complex reasoning, planning, and multi-agent collaboration with these models,” said Lu. “Under her guidance, I had the opportunity to collaborate with Children’s National Hospital to tackle the challenging task of clinical triage for complex medical documentation. This work led to a meaningful impact, where our solution performed comparably to professional human baselines and this experience ignited my passion for this field, and I am convinced that this research direction is both promising and impactful in the era of large models.”

Currently, he is exploring how multiple LLMs can collaborate effectively in dynamically changing environments through carefully crafted frameworks. 

“This involves designing LLM collaboration strategies that allow the models to act as intelligent agents within a data-driven environment, where they can extract, analyze, and interpret structured information from raw data sources. By tailoring these frameworks to real-world scenarios,” Lu said. “I work to enable LLMs to dynamically adapt their roles, share information efficiently, and solve complex, multi-layered problems. My research ultimately aims to create solutions that leverage data to guide the models’ collaborative strategies, achieving high performance in zero-shot and few-shot learning setups without extensive fine-tuning.”

Having earned a bachelor’s degree in electrical engineering from Hefei University of Technology, China, and a master’s degree in computer science from Northwestern University, Lu was attracted to Virginia Tech and the Sanghani Center by the professors’ expertise and many opportunities for quality collaborations to apply cutting-edge AI technology to real-world challenges.

In addition to Children’s National Hospital, Lu has had the opportunity to work with Amazon. These experiences haveallowed him to see – first-hand — how research can make a real difference. The guidance he received from experts, combined with access to high-quality research resources, has been invaluable in pushing the boundaries of his work with large language models, said Lu.

Projected to graduate in 2028, Lu hopes to join a research division of a major tech company in the United States. “I ameager to apply academic research to solve real-world problems and continue exploring the possibilities in AI,” he said.

As artificial intelligence (AI) increasingly affects peoples’ everyday lives, Hoda Eldardiry, associate professor in the Department of Computer Science and core faculty at the Sanghani Center for Artificial Intelligence and Data Analytics, is conducting research in engineering and computing education that will help students in majors such as computer science, computer engineering, and data science bridge the gap between the classroom and the job site.

Recently, she received a $349,360 grant from the National Science Foundation’s (NSF) Engineering Education program to support her work. 

“We want to ensure that every student is adequately prepared to not only confront but act on the challenges that new AI technologies pose to humans and society,” said Eldardiry. 

Read full story here.

Since his introduction as a character in the 1960s science fiction show “Star Trek,” Spock has had a worldwide impact on pop culture.

Masoud Agah, director of the Virginia Alliance for Semiconductor Technology, hopes to make an equal impact with his own SPOCK: the first-ever “miniature” chromatograph.

Although it sounds like something out of “Star Trek,” a chromatograph is a tool that analyzes the chemical composition of materials, such as water, soil, drugs, food, pollutants, and in the case of Agah’s size-segregated particle odor chromatograph kernel, or SPOCK, gases and aerosols. 

“It’s the first of its kind, a truly miniaturized platform,” said Agah, who is also the Virginia Microelectronics Consortium Professor in the Bradley Department of Electrical and Computer Engineering. “There’s no equivalent with this size platform that also measures the chemical composition and physical properties of aerosols.”

As the director of a research group focused on machine learning and core faculty at the Sanghani Center for Artificial Intelligence and Data Analysis, Hoda Eldardiry’s expertise in machine learning “on the edge” — an advancing field of research — helps make SPOCK possible.

Read full story here.

Two student Amazon Fellows and five faculty-led projects supported by the Amazon-Virginia Tech Initiative for Efficient and Robust Machine Learning for the 2024-25 academic year were named at a retreat held on the Blacksburg campus.

The initiative, launched in 2022 to advance research and innovation in artificial intelligence (AI) and machine learning, is funded by Amazon, housed in the College of Engineering, and directed by researchers at the Sanghani Center for Artificial Intelligence and Data Analytics on Virginia Tech’s Blacksburg campus and at the Virginia Tech Innovation Campus in Alexandria. 

Fellowships are awarded to Virginia Tech doctoral students recognized for their scholarly achievements and potential for future accomplishments. They must be enrolled in their second, third, or fourth year and interested in and currently pursuing educational and research experiences in AI-focused fields. In addition to receiving funding for their work, the fellowship includes an opportunity to interview for an Amazon internship intended to provide them with a greater understanding of industry and use-inspired research.

The initiative’s faculty awards support machine learning sponsored research that works toward revolutionizing the way the world uses and understands this field of modern technology.

Read full story here.

Thought leaders from academia and medical practice explored how artificial intelligence (AI) can advance children’s health care at the second annual Children’s National Hospital-Virginia Tech Symposium on AI for Pediatric Health at the Children’s National Research & Innovation Campus in Washington, D.C.

Rowland Illing, chief medical officer and director of international public sector health at Amazon Web Services (AWS), discussed the transformative impact of AI, machine learning, and cloud technology.

As a radiologist, Illing highlighted the example of how these tools enable clinicians to interpret screenings more quickly and accurately, addressing the growing global demand for faster diagnoses, better patient outcomes, and broader access to medical expertise.

He also highlighted the importance of collaboration to drive these advances.

Combined efforts between Virginia Tech and Children’s National are already yielding tangible results, said conference co-director Naren Ramakrishnan, director of the Sanghani Center for Artificial Intelligence and Data Analytics and the Thomas L. Phillips Professor in the Virginia Tech College of Engineering. 

Ramakrishnan emphasized the importance of expertise when integrating AI into pediatric health care.

Read full story here.

University Libraries at Virginia Tech and the University of California, Riverside, received a $115,398 Institute of Museum and Library Services grant to create a generative artificial intelligence incubator program (GenAI) to increase the adoption of artificial intelligence (AI) in the library profession and academic libraries. 

The incubator program aims to train librarians in generative artificial intelligence skills to improve library services.

“Libraries should play a role in demystifying AI and guiding the public in its use,” said Yinlin Chen, assistant director for the Center for Digital Research and Scholarship in the University Libraries at Virginia Tech, who is the principal investigator and grant project director.

Chen will use his expertise in advanced GenAI techniques and multidisciplinary AI research in his collaboration with Edward Fox, co-principal investigator and director of the digital library research laboratory at Virginia Tech and computer science professor, and Zhiwu Xie, co-principal investigator and assistant university librarian for research and technology at the University of California, Riverside, to create the generative artificial intelligence incubator program. They will build training materials, workshops, and projects to assist librarians in becoming AI practitioners.

Fox is a core faculty member at the Sanghani Center for Artificial Intelligence and Data Analytics. Read full story here.

A recent trailer for the upcoming Francis Ford Coppola film “Megalopolis” made headlines, but not for the reasons it was supposed to.

Meant to bolster the director’s image as an iconoclast, the trailer quoted negative critic reviews of some of Coppola’s masterpieces, such as “Apocalypse Now” and “The Godfather,” from the time the films were released. There was just one problem — the quotes weren’t real. The marketing consultant responsible for sourcing them had, evidently, generated them using artificial intelligence (AI).

This is hardly the first high-profile case of this particular form of AI — a large language model (LLM) — inventing and misattributing information. We’ve seen lawyers file briefs citing cases that don’t exist. These fabrications, or hallucinations, can be quite authoritatively written in a way that may sound plausible enough for people to accept without thinking twice. So when it comes to the future of AI-driven search tools, accuracy is paramount. That’s why, when The Washington Post decided to create such a tool to help users better access its own archive, it enlisted Naren Ramakrishnan, director of the Sanghani Center for Artificial Intelligence and Data Analytics, based at the Virginia Tech Innovation Campus in Alexandria.

Read full story here.

Physician scientists and researchers from Children’s National Hospital and Virginia Tech will increase efforts to harness artificial intelligence (AI) to help children who are struggling with medical conditions.

The innovators will meet in September at the Children’s National Research & Innovation Campus in Washington, D.C.

“It’s clear that harnessing the power of artificial intelligence is the way forward in advancing children’s health,” said Lance Collins, vice president and executive director of the Virginia Tech Innovation Campus in Alexandria. “Virginia Tech researchers are building momentum and solidifying our collaborative goals in this important area.” 

The effort involves Virginia Tech’s Sanghani Center for Artificial Intelligence and Data Analytics, Children’s National Hospital, and the Fralin Biomedical Research Institute at VTC, which has labs at the Children’s National Research & Innovation Campus. 

This meeting builds on the momentum from last year’s workshop, which featured sessions on smart surgery, rare diseases, and emergency medicine with talks by both Virginia Tech and Children’s National faculty and researchers. 

Read full story here.

Viruses like SARS-CoV-2 don’t respect boundaries, moving between species and continents and leaving destruction as they go. Beating the next pathogen with pandemic potential means getting good at crossing borders ourselves — between fields of study, between research universities, and between scientists and the wider community.

An $18 million grant announced by the U.S. National Science Foundation (NSF) will put that goal within reach. The award brings together five universities and more than 20 researchers, academics, and public health experts to establish the Virginia Tech-led Center for Community Empowering Pandemic Prediction and Prevention from Atoms to Societies (COMPASS).

Among those on board are Naren Ramakrishnan, the Thomas L. Phillips Professor of Engineering and director of the Sanghani Center for Artificial Intelligence and Data Analytics, and Anuj Karpatne, associate professor of computer science and core faculty at the center. Read full story here.