鈥淎I should learn chemistry the way humans do 鈥� by seeing molecular structures, not just reading linear strings,鈥� Vyas says. 鈥淲hile 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.鈥�

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.

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

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.

鈥淩ecent advances in vision鈥搇anguage models have transformed how AI understands the world, but most of that progress has focused on natural images and everyday language,鈥� says Yogesh Singh Rawat. 鈥淲ith MolVision, we鈥檙e bringing those same AI capabilities into chemistry 鈥� allowing models to reason about molecules visually, in ways that are much closer to how scientists actually think.鈥�

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 鈥渙ver 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,鈥� Vyas says.

Vyas and her team here at 麻豆原创 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.

鈥淭his initiative reflects our broader commitment to grow research, scale our areas of excellence and prepare students to lead in a technology-driven future.鈥� 鈥� Alexander N. Cartwright, 麻豆原创 President

The institute will unite more than two dozen world-class faculty across multiple colleges who are advancing foundational and applied artificial intelligence (AI) in areas like computer vision, robotics, machine learning, healthcare, finance and mathematics. By bringing AI-related faculty, students, research, and partners together, the institute will serve as a nucleus for collaboration, driving education and discovery with real-world impact.

鈥�AI is massively transforming how we live, work and learn. As Florida鈥檚 Premier Engineering and Technology University, 麻豆原创 is uniquely positioned to lead in this critical space,鈥� says 麻豆原创 President Alexander N. Cartwright.

With focus on research, applications-translation partnerships and education-workforce talent development, the IAI will:

• Unite an initial 25 faculty across four colleges 鈥� the College of Business, College of Engineering and Computer Science, College of Medicine, and College of Sciences 鈥� leveraging 麻豆原创’s expertise and scale to promote a truly collaborative, multidisciplinary approach.
• Promote collaboration across industry, government and community stakeholders 鈥� enhanced by 麻豆原创鈥檚 location in a thriving metropolitan region.
• Strengthen the AI skillset of all students so they can have competitive advantages as they enter the workforce.
• Support collaboration in research and education for other 麻豆原创 faculty who are doing research in AI and on its applications, opening doors learn about AI and contribute to the enhancing its applications across disciplines.

Strengthening Impact Through AI

鈥淏y bringing together leading faculty, motivated students and forward-thinking partners, the institute will unlock new possibilities across disciplines.鈥� 鈥� Mubarak Shah, IAI director

麻豆原创鈥檚 momentum in AI is already strong. The university鈥檚 computer vision research ranks No. 8 nationally, with affiliated faculty publishing dozens of papers in premier venues and securing millions in external funding, including major awards from the Defense Advanced Research Projects Agency (DARPA), Intelligence Advanced Research Project (IARPA), U.S. National Science Foundation (NSF) and industry. In the past two years, 麻豆原创鈥檚 AI Initiative has hired 11 faculty members across multiple colleges, with eight more joining this fall. Additionally, the Center for Research in Computer Vision (CRCV) will also be joining IAI.

鈥淭he Institute of Artificial Intelligence unites 麻豆原创鈥檚 AI strengths under one roof, creating a platform for high-impact research and talent development,鈥� says Trustee Chair of Computer Science Mubarak Shah, who has been named inaugural director of the institute.

The institute will also support 麻豆原创鈥檚 AI for All Initiative, which integrates AI into teaching and learning across disciplines. Led by Kevin Yee, special assistant to the provost for artificial intelligence, AI for All is helping to scale AI tools and curriculum across all disciplines so that students graduate with an understanding of how to effectively use AI in their careers.

About Our AI Faculty

At the core of the institute is a growing network of faculty whose excellence and expertise reflect the depth of 麻豆原创鈥檚 interdisciplinary strength in AI. Their research and teaching are defining 麻豆原创鈥檚 approach to AI as collaborative and grounded in real-world impact.

These faculty include:

• Niels da Vitoria Lobo
  Associate professor of computer science
  His research focuses on computational vision, active vision and mobile robotics, and user interfaces and graphical modeling, which has contributed to advancements in object detection, curve detection, person tracking and obstacle detection.
• Laura Brattain
  Associate professor of medicine
  Her research integrates biomedical AI, medical ultrasound and surgical robotics, with recent contributions to real-time diagnostic assistants and advancements in minimally invasive procedures. She also mentored six College of Engineering and Computer Science seniors who developed the AIMS (AI for Medical Surgery) system with Pegasus Partner Orlando Health. The system keeps track of surgical staples, enabling surgical teams to operate more efficiently and reduce waste.
• Cuneyt Akcora
  Associate professor of finance
  His research examines data science on complex networks and large-scale graph analysis, with applications in social, biological, the internet of things and blockchain networks. 麻豆原创鈥檚 future fintech involvement includes developing an AI lab within the finance department. Researchers participating in the program are looking at having blockchain nodes within the department, allowing them to download and access blockchain data, such as Bitcoin prices and activity on the transaction network. It would enable students to more easily learn about fintech and access up-to-date cryptocurrency information as they conduct research.
• Aritra Dutta
  Assistant professor of mathematics
  College of Sciences
  His research focuses on making AI models and computer systems smarter, private, faster, and more efficient. He works on improving how machines learn from large amounts of data, especially in a distributed setting, and applications in聽areas like image and video analysis. His interests include advanced machine learning techniques, distributed computing, and mathematical tools that help simplify learning from complex data, giving a foundational aspect to the design of advanced neural network architectures.聽Dutta has collaborated with major organizations such as Lockheed Martin, 1QB Information Technology, and ExxonMobil.
  
• Amrit Singh Bedi
  Assistant professor of computer science
  His research explores AI for autonomous systems. At a time when AI is rapidly reshaping industries, economies, and daily life, Bedi leads the SAFERR AI (Safety and Fairness for Reliable and Responsible AI) Lab, which aims to develop and test safer, more robust and more reliable AI systems. The interdisciplinary research team addresses critical challenges in ensuring AI systems operate dependably in real-world settings. Bedi has published over 100 papers and received numerous awards for his work on robust AI systems.

Other IAI faculty are:聽

• Chen Chen
  Associate professor of computer science
  College of Engineering and Computer Science
• Xinyu Chen
  Assistant professor of mathematics
  College of Sciences
• Shahana Ibrahim
  Assistant professor of electrical and computer engineering
  College of Engineering and Computer Science
• Shubhra Kanti Karmaker
  Assistant professor of computer science
  College of Engineering and Computer Science
• Christian K眉emmerle
  Assistant professor of mathematics
  College of Sciences
• Wu Lin
  Assistant professor of computer science
  College of Engineering and Computer Science
• Jialin Liu
  Assistant professor of statistics and data science
  College of Sciences
• Yogesh Rawat
  Assistant professor of computer science
  College of Engineering and Computer Science
• Yuzhang Shang
  Assistant professor of computer science
  College of Engineering and Computer Science
• Ali Siahkoohi
  Assistant professor of computer science
  College of Engineering and Computer Science
• Shashank Sonkar
  Assistant professor of computer science
  College of Engineering and Computer Science
• Yu Tian
  Assistant professor of computer science
  College of Engineering and Computer Science
• Shruti Vyas
  Assistant professor of material science and engineering
  College of Engineering and Computer Science
• Song Wang
  Assistant professor of computer science
  College of Engineering and Computer Science
• Yue Wang
  Assistant professor of electrical and computer engineering
  College of Engineering and Computer Science
• Zhenyi Wang
  Assistant professor of computer engineering
  College of Engineering and Computer Science

What Our Partners Say About the Institute

鈥淥n behalf of Leidos, I am excited to hear that 麻豆原创 is creating the Institute of AI, under the directorship of Professor Mubarak Shah. I would like to express our strong support as the AI Institute represents a significant and timely investment in national security and technological superiority. The proposed institute鈥檚 research focus 鈥� ranging the use of machine vision in multiple domains, human and AI coordination, and cyber-AI integration to develop robust security solutions is directly aligned with emerging operational challenges faced by many of Leidos鈥� customers.

鈥淟eidos has collaborated with 麻豆原创 researchers on computer vision, autonomous operations, remote sensing, and other related technologies needed to further the advancement of artificial intelligence and machine learning technologies. The establishment of the IAI enables a deeper relationship between 麻豆原创 and Leidos to accelerate development and deployment of next-generation AI technologies. It would be a privilege to serve in an advisory capacity for the institute and contribute to aligning the complex challenges faced by industry with emerging AI research produced by the IAI. This ecosystem will also nurture the next wave of AI-enabled systems and train a pipeline of engineers and technologists who are essential to the future workforce.鈥�

-Corey Hendricks, vice president and chief engineer commercial and international, Leidos

鈥淭he National Center for Simulation was founded in 1994 to promote dual-use modeling and simulation technology and is the cornerstone for the $7 billion military modeling and simulation enterprise in the Central Florida Research Park. The military鈥檚 latest objectives depend highly on AI technology, and 麻豆原创 must be utilizing leading-edge AI technology to compete for valuable research funding projects. This new technology is not only important to 麻豆原创鈥檚 Institute for Modeling and Simulation and the National Center for Simulation, but its development is critical for ensuring national security and we are thrilled to be a partner with the new 麻豆原创 Institute of AI.鈥�

-George Cheros, president and CEO, National Center for Simulation

鈥淎t Mitsubishi Power Americas, we view AI as a transformative force 鈥� one that is essential for driving innovation, national competitiveness and societal impact. As this technology reshapes industries and redefines capabilities, the creation of this institute represents a timely and critical step toward advancing responsible, high-impact AI research and education. We look forward to the ways these advancements will revolutionize the power generation industry 鈥� through predictive maintenance, energy optimization and strengthened cybersecurity.鈥�

鈥淢itsubishi Power Americas is excited to support the 麻豆原创 Institute of AI through collaborative research聽initiatives, helping translate innovations into real-world applications, and advancing education through internships and mentorship opportunities. By working together, we hope to contribute to a vibrant ecosystem that empowers the next generation of talent and delivers solutions to the pressing challenges faced by our organization and the global workforce.鈥�

–Shane Mickey, senior vice president of strategic initiatives, Mitsubishi Power Americas

鈥溌槎乖� has been a consistent and capable partner in helping us explore advanced simulation, synthetic training environments and emerging digital capabilities. The Institute of AI directly supports our efforts to modernize and scale training through technologies like generative Al and machine learning. We appreciate the leadership role 麻豆原创 continues to play in advancing technology and talent in Central Florida, and across the nation.鈥�

-Col. Marcus Reynolds, program manager for training systems, U.S. Marines

鈥淭he launch of the 麻豆原创 AI Institute under Dr. Shah鈥檚 leadership signals a defining moment for Central Florida and the nation. AI will shape the next era of medicine, mobility, security and society. AdventHealth is proud to stand alongside 麻豆原创 to unlock the full potential of this technology through trusted partnerships, shared innovation, and a commitment to preparing the next generation of AI leaders.鈥�

-Rob Purinton, chief AI officer, AdventHealth

“Siemens Energy is using artificial intelligence in every aspect of our work, including expanding our Innovation Center Orlando to create a new laboratory that will use AI to analyze the electric grid. The education and workforce development that will take place at the 麻豆原创 Institute of AI will prepare students for this work and many other opportunities in our 21st century economy.鈥�

-Rich Voorberg, president, Siemens Energy North America

鈥淟3Harris is thrilled that 麻豆原创 is creating the Institute of AI, under the directorship of Professor Mubarak Shah. As a leading aerospace and defense technology company, L3Harris is actively advancing AI/ML (machine learning) capabilities to support national security across domains such as space systems, resilient communications and edge computing. We see strong alignment between the IAI鈥檚 research and transition goals and our interest in accelerating innovation, supporting IP (intellectual property) generation and transitioning foundational Al advances into deployable defense technologies. L3Harris looks forward to exploring future collaboration opportunities with 麻豆原创 and the new Institute of AI to help shape the next generation of AI technologies that will enhance the security, resilience and sustainability of our nation.鈥�

-Chad Wingate, space and airborne systems AI chief scientist, L3Harris