Institute of Artificial Intelligence Archives | �鶹ԭ�� News

Atomic Vision: �鶹ԭ�� Researchers Create New AI Model for Molecular Analysis

Andrew Miller — Fri, 13 Feb 2026 12:19:07 +0000

At the �鶹ԭ�� Institute of Artificial Intelligence (IAI), researchers have developed MolVision, a new artificial intelligence (AI) vision language (VLM) model capable of accurately viewing a molecule’s structure. The project was launched from a bold idea, to make AI models learn scientific principles the same way students do. Leading the study is Assistant Professor of Materials Science and Engineering Shruti Vyas. The MolVision research team includes Associate Professor of Computer Science and IAI member Yogesh Singh Rawat and Deepan Adak, a researcher from the National Institute of Technology, Kurukshetra.

“AI should learn chemistry the way humans do — by seeing molecular structures, not just reading linear strings,” Vyas says. “While large language models have shown promise for molecular property prediction, their reliance on representations like SMILES or SELFIES [textual representations] limits their ability to capture the rich structural cues chemists rely on.”

According to Vyas, this work opens a new pathway for chemical predictions and molecular analysis, by creating an AI system that operates more intuitively.

A Challenging Vision

According to Vyas, one of the biggest challenges facing the field of artificial intelligence and computer vision is in shifting AI models from a textual to a visual understanding of chemical reactions.

“Molecular images represent a very different data domain compared to the natural images or text that vision-language models are typically trained on.” Vyas says, “Molecules contain highly specific structural relationships — bonding patterns, stereochemistry, and functional group arrangements — that are subtle yet crucial for property prediction.”

Many VLM models have limited exposure to visual representations of scientific data, which makes training and adapting them to understand the nuances of molecules and their atomic structure a primary challenge.

Transforming How Scientists and AI See Chemistry

To address these challenges, Vyas and her research team developed a multi-modal data set for MolVision to refer to during its training. The data set pairs 2D diagrams with text-based descriptions on a variety of molecules and different atomic structures. Using this data set was crucial for training the MolVision VLM to integrate textual and visual information effectively. Using a LoRA (low rank adaptation) algorithm, the MolVision VLM is able to engage in billions of parameters worth of data enabling it to complete complex tasks such as molecular property prediction or chemical description without the cost of full retraining.

“Recent advances in vision–language models have transformed how AI understands the world, but most of that progress has focused on natural images and everyday language,” says Yogesh Singh Rawat. “With MolVision, we’re bringing those same AI capabilities into chemistry — allowing models to reason about molecules visually, in ways that are much closer to how scientists actually think.”

This work has the potential to transform drug discovery, the personalization of medicine, and even sustainable design and engineering. The research team also expects that “over the next few years we can expect this multimodal approach to reduce experimental screening burdens, support faster identification of promising drug candidates and materials, and offer more interpretable insights into structure-property relationships,” Vyas says.

Vyas and her team here at �鶹ԭ�� plan to scale up the MolVision VLM project in terms of its data set and capabilities. The team plans to integrate the VLM model in chemistry with technologies using current AI neural networks and large molecular simulators to create hybrid systems that can combine symbolic, visual and physical reasoning.

Vyas will also participate in the upcoming where she will be presenting an exhibit on AI for chemistry and molecules. Those interested in viewing the exhibit can attend from 7:45 to 11:00 p.m. this Saturday on the 4th Floor.

Could AI Lead to The Fountain of Youth?

Robert Stephens — Tue, 03 Feb 2026 14:37:25 +0000

Every day, Yu Tian clocks in to his AI and Imaging in Medicine (AIM) Research Lab at �鶹ԭ�� working to change life as we know it.

“We often hear that ‘we’re at a turning point in human history,’” Tian says, “and with AI research in a university setting like this, it’s true.”

This is just one example of AI innovations at �鶹ԭ��. Learn about more at the .

Tian has adapted quickly — and gladly — to life at �鶹ԭ�� since arriving last May to teach computer science. He is now living what he once imagined as the idyllic scenario: talented artificial intelligence (AI) specialists coming from around the world to collaborate with medical experts and launch new projects, pressing each other through formidable challenges and achieving the unachievable.

“The ultimate goal for my team is to extend people’s lives, significantly,” Tian says.

Assembling a Dream Team

Tian’s ambition has eluded human pursuits for millennia. Even medical AI has barely begun to approach its potential impact — especially when compared with other AI applications like chatbots and fintech.

“There are two major limitations with medical AI,” Tian says. “One is the privacy of data — AI requires a lot of data. The other issue holding back progress is collaboration. Computer scientists working on AI typically don’t know medicine. We need input from doctors and biologists. In that sense, universities are uniquely positioned.”

“Universities bring together computer scientists, physicians and hospitals — allowing us to identify clinically meaningful problems, access real-world data responsibly and develop solutions that are grounded in medical practice.”

With all of this available to his AIM team, they’ve been building a system that can learn from each patient’s history, exams, MRIs, CTs and life information. Given the copious amount of data, the AI model would then predict the person’s future medical trajectory.

For example, a doctor could know the probability of dementia five years before onset. An oncologist could use MRI scans to determine the gene mutation associated with a tumor within seconds rather than performing surgery and then waiting weeks for the results of a genome test.

Diseases would be preventable. Treatment plans would be more effective and less costly. People would be healthier, happier and live longer.

How close are we?

“Close,” Tian says. “It’s sometimes hard for me to believe, too.”

At the Forefront of AI

As recently as 2020, Tian didn’t give much thought to topics like longevity or the location of Orlando.

While working to complete his Ph.D., Tian had immersed himself in familiar computer-science objectives at the University of Adelaide in Australia. Day and night, the lab became a replacement for the home he’d left on the Chinese peninsula of Liaodong. In just three years, he published more than 15 papers.

Yet something was missing: a greater purpose.

“I’ve always wanted to discover a solution to a mystery that has never been solved,” he says.

He didn’t know what that mystery might be until an advisor asked him, “Do you want to work on fun AI video projects, or do you want to really impact lives?”

Left to right: Computer science doctoral students Dannong Wang,
Assistant Professor of Computer Science Yu Tian, Tianxingjian Ding and Abdul Mohaimen Al Radi. (Photo by Antoine Hart)

The conversation grabbed Tian’s attention. He’d been reading about groundbreaking AI research in computer vision and medical imaging. Many of the papers came from an institution in the U.S., a place called �鶹ԭ��.

After finishing his Ph.D., Tian came to the U.S. for postdoctoral work at Harvard University and the University of Pennsylvania, digging his attention deeper into not only medical AI, but also into �鶹ԭ��.

“I found out about �鶹ԭ��’s young medical school with physicians and scientists working together. And then I heard about the hospitals in the Orlando area, including AdventHealth and Orlando Health, and this freedom to explore AI applications. I wanted to be in an environment like that, where research can advance quickly.”

Tian fast-tracked his postdoctoral role so he could accept a position at �鶹ԭ��, participate in the collaboration, and continue his pursuit of the unsolved mystery: extend life. Shortly after he arrived, the Institute of Artificial Intelligence (IAI) opened its doors — and Tian went on to establish his lab, taking a significant step toward his long-term research goals.

Big Goals Leads to Big Impact

You can sense a profound energy inside AIM.

It’s a convergence of talent and enthusiasm. In addition to Tian, the institute has recruited two dozen faculty, more than 100 doctoral students and 10 postdocs to imagine and encourage progress. The expertise transcends domains, including computer science, robotics, finance, smart cities and medicine.

“We all have big goals,” Tian says.

Less than a year after heading up the AIM Lab, he says, “We aren’t far off from deploying AI models in hospitals to help doctors.”

Tian works at the same speed as technology (fast), until a certain topic comes up. Family. He looks up and begins to describe his hometown, his mother, and the sight of his dad walking in the door one night with the family’s first computer.

“He and I were fascinated. We went from trying to install the first software to building our own computers and robots. I could never get enough of it.”

Those memories motivate him to work even faster toward his ultimate goal.

“I want to help everyone have a quality life to 100 — or longer. My family. Me. All of us,” he says. “I love the possibility. I love being here, at this turning point, with the opportunity to make a huge impact.”

�鶹ԭ��’s Major Milestones of 2025

Juzanne Martin — Mon, 29 Dec 2025 14:00:07 +0000

�鶹ԭ�� continues to dare, to dream and to build what’s next. In 2025, that bold spirit powered major milestones across academics, research, athletics and the community — proving once again that when Knight Nation aims higher, it redefines what’s possible.

Here are the highlights that shaped an unforgettable year.

Daring to Boldly Invent the Future: Florida’s Next-Generation Preeminent University

�鶹ԭ�� met the 12 metrics required to earn the Preeminent State Research University designation from the Florida Board of Governors, the highest designation for state research universities. This landmark achievement highlights sustained progress in student success, research and more — affirming �鶹ԭ��’s leadership in advancing opportunity and impact in Florida and beyond.

�鶹ԭ�� Opens Dr. Phillips Nursing Pavilion in Lake Nona, Fueling a Talent Pipeline and Healthcare Innovation

�鶹ԭ�� opened the Dr. Phillips Nursing Pavilion on the Academic Health Sciences Campus at Lake Nona — a 90,000-square-foot state-of-the-art facility dedicated to preparing the next generation of healthcare professionals. The pavilion expands immersive simulation technology and interdisciplinary learning spaces, enabling �鶹ԭ�� to graduate more nurses ready to serve communities across the region.

Pegasus Partners Expand with BNY and Lockheed Martin

This year saw strategic growth of �鶹ԭ��’s Pegasus Partners program, with major collaborations forged with global financial services company BNY and aerospace and defense leader Lockheed Martin. The BNY co-located educational innovation hub on �鶹ԭ��’s main campus — the first of its kind in Florida — brings experiential learning and cybersecurity education directly to students. Additionally, the expanded Lockheed Martin partnership will grow the highly successful College Work Experience Program and expand research in vital areas such as artificial intelligence, robotics and hypersonic technologies.

Elevating Impact Across Space

As America’s Space University, �鶹ԭ�� deepened its influence across the space sector this year, highlighted by the inaugural �鶹ԭ�� Space Week that took place Nov. 3-7. The university-wide celebration showcased all the ways Knight Nation is advancing space research, supporting Florida’s fast-growing space economy, and preparing the next generation of explorers, engineers, and entrepreneurs. The observance also marked the debut of the SpaceU Awards, which celebrated eight honorees — two students, three faculty, two organizations and a record-setting astronaut — for pushing the boundaries of what’s possible in space development, discovery and exploration.

�鶹ԭ��’s impact also extended into human health in space. Two internationally known  experts — William Powers and Jennifer Fogarty — joined the College of Medicine’s faculty as part of �鶹ԭ��’s new Center for Aerospace and Extreme Environments Medicine that will lead research and technology development for improving health in extreme environments such as space.

As the top talent provider to the nation’s aerospace and defense industries, �鶹ԭ�� also launched a new online space MBA program to meet the expanding needs of the booming space industry on Florida’s Space Coast and around the world. The 24-month part-time graduate business program focuses on space commercialization, business strategy and innovation, preparing graduates to lead in high-impact roles across the commercial space, aerospace, government, startups and emerging tech industries.

�鶹ԭ�� Launches Institute of Artificial Intelligence to Advance Research, Talent Development Across Disciplines

�鶹ԭ�� launched the Institute of Artificial Intelligence, a new university-wide initiative bringing together top faculty, industry partnerships and cross-campus collaboration to position the university as a national leader in AI. The institute will also support �鶹ԭ��’s AI for All Initiative, which integrates AI into teaching and learning across disciplines, ensuring students graduate with the ability to use AI effectively in their careers.

Honoring Excellence on Founders’ Day

�鶹ԭ��’s annual Founders’ Day honored the outstanding achievements of the university’s employees, faculty and students. Hundreds of Knights were recognized for their excellence and impact — among them Pegasus Professors Roger Azevedo, Fevzi Okumus and Yan Solihin; Medal of Societal Impact honoree Mohamed Abdel-Aty; Reach for the Stars honorees Amrita Ghosh, Leland Nordin, Yogesh Rawat and Kelly Stevens; and 37 Order of Pegasus inductees — the university’s highest student honor.

Epic Universe Launch Provides Immersive Learning Opportunities at �鶹ԭ��

Universal Orlando Resort’s highly anticipated new theme park, Epic Universe, opened its gates this spring, and Knights played a role in bringing it to life. Located less than a mile away, �鶹ԭ��’s — ranked No. 1 in the world for hospitality education (CEOWORLD magazine) — turned Epic Universe into a living case study for hands-on learning in hospitality, themed experience, engineering and beyond. While the park attracts millions of guests with its immersive worlds and attractions, it’s also transforming hospitality education for Rosen College students, building a direct talent pipeline into the park and developing a workforce ready to lead the industry.

Introducing John Buckwalter, �鶹ԭ��’s Next Provost 

Following a competitive national search, John Buckwalter was appointed �鶹ԭ��’s next provost and executive vice president for academic affairs. He and his wife, Amalia, officially joined Knight Nation on Aug. 1. Buckwalter brings more than 20 years of experience in academia to �鶹ԭ��. He most recently served as provost at Boise State University, where he led transformative interdisciplinary initiatives and championed student achievement. He succeeds Provost Michael D. Johnson, who retired this summer following 35 years of service to �鶹ԭ��.

Knights Shine in Athletics

�鶹ԭ�� Athletics delivered unforgettable moments this year — from the rowing team claiming its first Big 12 Championship in program history, to men’s soccer’s conference title, to men’s tennis clinching its , to 82-78 victory over Hofstra at Additional Financial Arena that sparked the best start (8-1) in head coach Johnny Dawkins’ tenure.

Together, We Unleashed Impact: Thank You, Knight Nation, for a Transformational Day of Giving 2025

Knights made a collective impact for another record-breaking celebration of all things Black & Gold. raised more than $14.8 million — a 63% increase from last year and the most in university history. With 10,472 gifts, inspired donors across the globe rallied together for the community-driven effort — fueling �鶹ԭ��’s academic programs, life-changing scholarships, groundbreaking research and more. These contributions were made across all 50 U.S. states, as well as globally, including Australia, France, Panama and the United Kingdom.

�鶹ԭ�� Team Places in Top 10 at Global Machine Learning Competition

Marisa Ramiccio ’11 — Mon, 15 Dec 2025 15:31:49 +0000

A team of �鶹ԭ�� researchers placed eighth in the 2025 EEG Challenge, a global machine learning competition that asks participants to predict behavioral responses from brain data. The Knights, who call themselves Team Marque, bested 8,400 submissions, including those from research labs and tech companies like Meta and Emotiv.

The winning team includes Mubarak Shah, the director of the �鶹ԭ�� Institute of Artificial Intelligence (IAI); Helen Huang and Qiushi Fu, associate professors of biomedical engineering; Yue Wen, an assistant professor of biomedical engineering; Abhilash Durgam, a doctoral student who works in the Center for Research in Computer Vision; and Jerry Fu, a postdoctoral scholar mentored by Huang and Wen.

As top 10 winners, Team Marque’s code will be added to the competition’s open-source repository, contributing to the future advancement of EEG research. They also receive a certificate in recognition of their achievement. Shah says that placing in the top 10 at the world’s premier venue for AI and machine learning is a tremendous accomplishment for �鶹ԭ�� and its newly established IAI.

“It speaks to the strength of �鶹ԭ��’s interdisciplinary culture,” Shah says.

“Our students and faculty, with their combined expertise in machine learning, neuroscience, signal processing and computer vision can compete with some of the world’s best teams.” — Mubarak Shah, Trustee Chair Professor

The competitors had to prevail in two individual challenges that utilized data from the Healthy Brain Network, which includes EEGs of more than 3,000 children who were multitasking. Challenge 1 asked the teams to improve the predicted reaction time of a subject seeing change in contrast of an image while Challenge 2 called for an improved prediction of mental health traits in a subject.

Durgam says the secret to Team Marque’s success was to look for the patterns that hold true for all people.

“Rather than treat this as a regression problem to predict a number, we used a classification approach where we taught our model to recognize the unique ‘profile’ of the person,” Durgam says. “This encouraged the model to understand the individual’s distinct characteristics rather than just treating the task as a simple math problem.”

The team’s efforts are more than just an accomplishment for themselves and for the university — their code can now be used by scientists to advance EEG research.

“Our open-source repository supports open-science efforts, which I believe is necessary to make substantial breakthroughs in EEG research at a faster rate than any one group could accomplish alone,” Huang says. “Being able to predict mental health traits in developing children is a challenging problem that has great societal impact and could be solved faster collectively as a field by working in parallel and sharing data and code so groups don’t have to repeat something that has already been tried.”

Team Marque came together after Durgam reached out to Huang to learn more about EEG. Each of them had already formed teams for the competition, but decided to combine efforts for better results. For Huang, the competition also had a personal connection as one of the organizers, Seyed Yahya Shirazi ’21PhD, is her former student.

“I don’t think we have been in the top 10 if we didn’t combine efforts,” Huang says. “Together, we could work in parallel to explore fundamentally different approaches first to identify the most promising one and then focus on optimizing specific parameters.”