A new agreement between Los Alamos National Laboratory (LANL) and the National Science Foundation’s Artificial Intelligence Institute for Advances in Optimization (AI4OPT) at Georgia Tech is set to propel research in applied artificial intelligence (AI) and engage students and professionals in this rapidly growing field.

“This collaboration will help develop new AI technologies for the next generation of scientific discovery and the design of complex systems and the control of engineered systems,” said Russell Bent, scientist at Los Alamos. “At Los Alamos, we have a lot of interest in optimizing complex systems. We see an opportunity with AI to enhance system resilience and efficiency in the face of climate change, extreme events, and other challenges.”

The agreement establishes a research and educational partnership focused on advancing AI tools for a next-generation power grid. Maintaining and optimizing the energy grid involves extensive computation, and AI-informed approaches, including modeling, could address power-grid issues more effectively.

AI Approaches to Optimization and Problem-Solving

Optimization involves finding solutions that utilize resources effectively and efficiently. This research partnership will leverage Georgia Tech's expertise to develop “trustworthy foundation models” that, by incorporating AI, reduce the vast computing resources needed for solving complex problems.

In energy grid systems, optimization involves quickly sorting through possibilities and resources to deliver immediate solutions during a power-distribution crisis. The research will develop “optimization proxies” that extend current methods by incorporating broader parameters such as generator limits, line ratings, and grid topologies. Training these proxies with AI for energy applications presents a significant research challenge.

The collaboration will also address problems related to LANL’s diverse missions and applications. The team’s research will advance pioneering efforts in graph-based, physics-informed machine learning to solve Laboratory mission problems.

Outreach and Training Opportunities

In January 2025, the Laboratory will host a Grid Science Winter School and Conference, featuring lectures from LANL scientists and academic partners on electrical grid methods and techniques. With Georgia Tech as a co-organizer, AI optimization for the energy grid will be a focal point of the event.

Since 2020, the Laboratory has been working with Georgia Tech on energy grid projects. AI4OPT, which includes several industrial and academic partners, aims to achieve breakthroughs by combining AI and mathematical optimization.

“The use-inspired research in AI4OPT addresses fundamental societal and technological challenges,” said Pascal Van Hentenryck, AI4OPT director. “The energy grid is crucial to our daily lives. Our collaboration with Los Alamos advances a research mission and educational vision with significant impact for science and society.”

The three-year agreement, funded through the Laboratory Directed Research and Development program’s ArtIMis initiative, runs through 2027. It supports the Laboratory’s commitment to advancing AI. Earl Lawrence is the project’s principal investigator, with Diane Oyen and Emily Castleton joining Bent as co-principal investigators.

Bent, Castleton, Lawrence, and Oyen are also members of the AI Council at the Laboratory. The AI Council helps the Lab navigate the evolving AI landscape, build investment capacities, and forge industry and academic partnerships.

As highlighted in the Department of Energy’s Frontiers in Artificial Intelligence for Science, Security, and Technology (FASST) initiative, AI technologies will significantly enhance the contributions of laboratories to national missions. This partnership with Georgia Tech through AI4OPT is a key step towards that future.

Building on the Foundation of Success

CSSE, founded in late 2021 and supported by Schmidt Sciences as part of their VISS initiative, was created to advance and support scientific research by applying modern software engineering practices, cutting-edge technologies, and modern tools to the development of scientific software within and outside Georgia Tech. CSSE is led by Alex Orso,  professor and associate dean in the College of Computing,  and Jeff Young, a principal scientist at Georgia Tech. The Center's team boasts over 60 years of combined experience, with engineers from companies such as Microsoft, Amazon, and various startups, working under the supervision of the Center’s Head of Engineering, Dave Brownell. Their focus is on turning cutting-edge research into real-world products.

“Software engineering is about much more than just writing code,” Orso explained. “It’s also about specifying, designing, testing, deploying, and maintaining these systems.”

A Partnership to Support AI Research and Innovation

Through this collaboration, CSSE’s expertise will be integrated into Tech AI to create a software engineering division that can support AI engineering and also create new career opportunities for students and researchers.

Pascal Van Hentenryck, the A. Russell Chandler III Chair and professor in the H. Milton Stewart School of Industrial Engineering (ISyE)  and director of both the NSF AI Research Institute for Advances in Optimization (AI4OPT) and Tech AI, highlighted the potential of this partnership.

“We are impressed with the technology and talent within CSSE,” Van Hentenryck said. “This partnership allows us to leverage an existing, highly skilled engineering team rather than building one from scratch. It’s a unique opportunity to build the engineering pillar of Tech AI and push our AI initiatives forward, moving from pilots to products.”

“Joining our forces and having a professional engineering resource within Tech AI will give Georgia Tech a great competitive advantage over other AI initiatives,” Orso added.

One of the first projects under this collaboration focuses on AI in energy, particularly in developing new-generation, AI-driven, market clearing optimization and real-time risk assessment. Plans are also in place to pursue several additional projects, including the creation of an AI-powered search engine assistant, demonstrating the center’s ability to tackle complex, real-world problems.

This partnership is positioned to make a significant impact on applied AI research and innovation at Georgia Tech. By integrating modern software engineering practices, the collaboration will address key challenges in AI deployment, scalability, and sustainability, and translate AI research innovations into products with real societal impact.

“This is a match made in heaven,” Orso noted, reflecting on the collaboration’s alignment with Georgia Tech’s strategic goals to advance technology and improve human lives. Van Hentenryck added that “the collaboration is as much about creating new technologies as it is about educating the next generation of engineers.”

Promoting Open Source at Tech AI

A crucial element supporting the new Tech AI and CSSE venture is Georgia Tech’s Open Source Program Office (OSPO), a joint effort with the College of Computing, PACE, and the Georgia Tech Library. As an important hub of open-source knowledge, OSPO will provide education, training, and guidance on best practices for using and contributing to open-source AI frameworks.

“A large majority of the software driving our current accomplishments in AI research and development is built on a long history of open-source software and data sets, including frameworks like PyTorch and models like Meta’s LLaMA,” said Jeff Young, principal investigator at OSPO. “Understanding how we can best use and contribute to open-source AI is critical to our future success with Tech AI, and OSPO is well-suited to provide guidance, training, and expertise around these open-source tools, frameworks, and pipelines.”

Looking Ahead

As the partnership between Tech AI and CSSE evolves, both groups anticipate a future in which interdisciplinary research drives innovation. By integrating AI with real-world software engineering, the collaboration promises to create new opportunities for students, researchers, and Georgia Tech as a whole.

With a strong foundation, a talented team, and a clear vision, Tech AI and CSSE together are set to break new ground in AI and scientific research, propelling Georgia Tech to the forefront of technological advancement in the AI field.

About the Center for Scientific Software Engineering (CSSE)

The CSSE at Georgia Tech, supported by an $11 million grant from Schmidt Sciences, is one of four scientific software engineering centers within the Virtual Institute for Scientific Software (VISS). Its mission is to develop scalable, reliable, open-source software for scientific research, ensuring maintainability and effectiveness. Learn more at https://ssecenter.cc.gatech.edu.

About Georgia Tech’s Open Source Program Office (OSPO)

Georgia Tech’s OSPO supports the development of open-source research software across campus. Funded by a Sloan Foundation grant, OSPO provides community guidelines, training, and outreach to promote a thriving open-source ecosystem. Learn more at https://ospo.cc.gatech.edu.

About Schmidt Sciences

Schmidt Sciences is a nonprofit organization founded in 2024 by Eric and Wendy Schmidt that works to advance science and technology that deepens human understanding of the natural world and develops solutions to global issues. The organization makes grants in four areas—AI and advanced computing, astrophysics and space, biosciences and climate—as well as supporting researchers in a variety of disciplines through its science systems program. Learn more at https://www.schmidtsciences.org/. 

About Tech AI

Tech AI is Georgia Tech’s AI hub, advancing AI through research, education, and responsible deployment. The hub focuses on AI solutions for real-world applications, preparing the next generation of AI leaders. Learn more at https://ai.gatech.edu.

She did both while strengthening her coding knowledge during her time as a camper and mentor at the Seth Bonder Camp in Computational and Data Science for Engineering (SBC).

“I did it when it was fully virtual, and it was definitely an experience,” said Sweeny who spent a week being introduced to computing and data science where she performed virtual activities, last June.

The camp, which is offered either as an online course or on-campus summer camp at Georgia Tech, is designed to build students’ problem-solving and analytical skills while furthering their interest in computer science as a potential career. It is also part of AI4OPT’s mission to inspire young Georgians to pursue STEM (science, technology, engineering and mathematics).

AI4OPT hosted its first in-person summer camp at Georgia Tech in June. The camp brought together 60 students from schools across Georgia including Drew Charter, Banneker High School, and Westlake High School.

Sweeny was asked to return to this particular camp—but this time, as a mentor.

“Of course, I said yes, because it was something fun that I could do over the summer preparing for college without it being too hefty,” said Sweeny. “It was something that I felt prepared for from attending the camp.”

Responses like Sweeny’s motivates SBC Site Managers like Reem Khir to introduce more bright minds to the camp centered around computer programming logic, programming language for AI, and teamwork.

“We expose them [high school students] to certain types of education areas like Twitter analysis, how to solve a sudoku, and even computational biology, if they wanted to consider a career in biology,” said Khir, who joined the camp last year to help students with assignments. This year, she took on even bigger leadership role by maintaining and observing two camps and facilitating 50 students and seven teaching assistants (TAs). She worked under a ‘student to student and student to TA’ interactive structure so that each participant took away a useful skill in data science.

“It’s the time where high school students start forming opinions and decisions about the career path they want to pursue,” said Khir. “The steppingstone is their college education, and we can help students in that period.”

AI4OPT Will Acquire and Advance Seth Bonder Camp

AI4OPT is working to adopt a short-term system used to track students after the camp. The institute wants to build up the system to see majors, colleges, and career paths each student has vowed to pursue before they head off to college or the workforce.

“This is a critical period for students,” said Khir. “It’s a time where students start thinking about a major for college and later impacting the next 20 or 30 years of their life. Being a part of that is very unique in terms of creating a positive influence in the next generation.”

AI4OPT is taking the lead over the SBC to offer the initiative more organizational support as the program has seen tremendous growth and has become a much broader initiative. The Seth Bonder Foundation, which first introduced the camp to those ages 10-18, will continue to fund the camp now more targeted towards high school students interested in engineering, but do not have access to computer science and/or data science in their middle and high schools.

“A lot of the different communities are not exposed to this and may never see this opportunity. The Seth Bonder Camp exposes high school students to AI opportunities and gives them skills to successfully enter the field of STEM with confidence,” said Professor Pascal Van Hentenryck, who’s brought his data sciences skills and knowledge to Georgia Tech and leads both AI4OPT and the SBC.

AI4OPT is in transition to lead the SBC to offer more organizational support as the program sees tremendous growth. The research Institute will expand the longitudinal camps to engage middle and high school students in these topics, while also bringing AI education and research programs to HBCU’s and Hispanic-serving colleges throughout the nation, addressing the widening gap in job opportunities.

Though Sweeny has transitioned away from coding and transcended into research, she never stopped setting goals even now as a first-year biomedical engineering major at Georgia Tech.

“Do anything you can to take it [the SBC] even if you don't want to go into coding,” said Sweeny. “It is a good way to meet new people learn new skills, it is something that you don't necessarily have to have a love for coding to have to do it.”

To learn more about the Seth Bonder Camp in Computational and Data Science for Engineering and to partner with the camp, visit sethbondercamp.isye.gatech.edu.

(Writer’s note: This article is part of a series highlighting AI4OPT members, students, education programs and professional development testimonies.)

Most LLMs look similar on the outside. However, they can be very different under the hood. Individual LLMs are often trained on proprietary datasets, optimized using varying methodologies, and built with unique architectures.

While the responses from Google’s Gemini 1.5 Flash, OpenAI’s ChatGPT-4, and Meta AI are mostly in sync, comparing responses from different LLMs can reveal unique insights, potential blind spots, and areas of consensus. Comparing them can also:

• Illustrate how different models handle complex, forward-looking questions
• Test their ability to reason, synthesize, and extrapolate
• Highlight their strengths and weaknesses in dealing with speculative or ambiguous topics

The following responses were generated using the query, What do you believe will be the most significant breakthrough in AI in 2025? As most users know, LLMs can be chatty, so the responses have been edited for length and style.

Gemini 1.5 Flash

Here are a few areas where we might see significant leaps:

AI for Science: Expect to see AI accelerate scientific discovery across fields like drug development, materials science, and climate modeling. This could involve AI designing new molecules, predicting material properties, and analyzing complex climate data.

AI for Healthcare: We might witness breakthroughs in AI-powered diagnostics, personalized medicine, and robotic surgery. Imagine AI systems that can accurately predict disease risk, develop personalized treatment plans, and assist surgeons with increased precision.

AI for Robotics: Advancements in AI could lead to more sophisticated and autonomous robots. This could include robots capable of performing complex tasks in manufacturing, logistics, and even household chores.

AI for Accessibility: AI has the potential to significantly improve the lives of people with disabilities. We could see breakthroughs in AI-powered assistive technologies, such as real-time translation services, personalized learning tools, and AI-driven mobility aids.

ChatGPT-4

Predicting breakthroughs in AI is speculative, but based on current trends, some likely candidates for significant advancements in 2025 include:

Generative AI for Personalized Medicine: AI's ability to model and simulate biological systems could lead to personalized treatments, drug discovery, and diagnostic breakthroughs. Models like AlphaFold have paved the way, and further progress might enable real-time, AI-driven medical recommendations.

Autonomous Systems in Complex Environments: Thanks to advancements in reinforcement learning and multimodal AI systems, autonomous vehicles, drones, and robots could become more proficient in navigating unstructured or unpredictable environments. This could revolutionize logistics, disaster response, and even personal transportation.

AI-Driven Creativity and Collaboration Tools: AI tools that co-create with humans across mediums like art, writing, coding, and design could reach new heights in usability and sophistication. These systems may transition from assistive to collaborative partners in creative processes.

Foundation Models for Specialized Fields: Fine-tuning foundation models for niche industries like law, finance, and education could drive transformative efficiencies. For instance, legal-specific AI might draft contracts or analyze case law at unprecedented speeds.

Advances in Explainable AI (XAI): Efforts to make AI more transparent and interpretable could yield significant breakthroughs, particularly in sectors like healthcare, finance, and autonomous systems, where trust and accountability are critical.

Fusion of Quantum Computing and AI: If quantum computing hardware progresses, its integration with AI could solve problems previously considered computationally infeasible, such as simulating complex systems or optimizing supply chains.

Meta AI

The most significant breakthrough in AI for 2025 is expected to be the widespread adoption of generative AI (GenAI). This technology can potentially revolutionize various industries, from healthcare and education to media and entertainment.

One key area where GenAI will significantly impact industry is industrial automation. Siemens, a leading technology company, is already working on integrating GenAI into its industrial automation systems, which will enable faster and more efficient decision-making processes.

Another significant breakthrough will be the increased use of AI agents. These agents, powered by GenAI, can complete tasks with minimal human intervention, increasing productivity and efficiency gains in various industries.

Additionally, adopting GenAI will lead to significant advancements in edge computing, enabling faster and more efficient data processing at the network's edge.

Overall, the widespread adoption of GenAI in 2025 will profoundly impact various industries, leading to increased efficiency, productivity, and innovation.

Van Hentenryck serves as the A. Russell Chandler III Chair and Professor in Georgia Tech’s H. Milton Stewart School of Industrial and Systems Engineering. He is also the director of Tech AI, Georgia Tech’s new strategic hub for artificial intelligence, and the U.S. National Science Foundation AI Institute for Advances in Optimization (AI4OPT), which operates under Tech AI’s umbrella.

In his talk, “AI for Social Good,” Van Hentenryck showcased how AI technologies can drive impact across key sectors—including mobility, education, healthcare, disaster response, and e-commerce. Drawing from ongoing research and real-world deployments, he emphasized the critical role of human-centered design and interdisciplinary collaboration in developing AI that benefits society at large.

“AI has tremendous potential to serve the public good when guided by ethics, equity, and purpose-driven innovation,” said Van Hentenryck. “At Georgia Tech, our work aims to harness this potential to create meaningful change in people’s lives.”

The event marked the debut of Giga Talks, a new speaker series designed to convene global thought leaders, engineers, and policymakers around timely issues in technology and innovation. The initiative supports Giga’s broader mission to connect every school in the world to the internet and unlock digital opportunities for children everywhere.

A video recording of Van Hentenryck’s talk is available on here.

The three-day international festival convened leading researchers, industry experts, and members of the public to explore how artificial intelligence is shaping science, technology, and society. Through keynote talks, panels, and interactive sessions, the event fostered dialogue around emerging AI research, real-world applications, and societal impact.

Van Hentenryck delivered a keynote on “AI for Engineering Optimization” during Day 1: Research, which focused on recent advances in foundational and applied AI. His talk highlighted how AI and optimization methods can be integrated to address complex engineering challenges, with implications for domains such as energy systems, mobility, and large-scale decision-making. 

The session was chaired by Nysret Musliu of TU Wien and the Cluster of Excellence Bilateral AI (BilAI).

The research-focused first day of the festival featured discussions on topics including neurosymbolic AI, large language models, explainable AI, AI in science, and automated problem solving and decision-making. Van Hentenryck’s keynote contributed to these conversations by emphasizing the role of AI-driven optimization in advancing engineering design and operational efficiency.

AI Festival 2025 was co-organized by TU Wien, the Center for Artificial Intelligence and Machine Learning (CAIML), BilAI—funded by the Austrian Science Fund (FWF)—the Vienna Science and Technology Fund (WWTF), and TU Austria. The event underscored the importance of international collaboration across academia and industry in advancing responsible and impactful AI research.

Van Hentenryck’s participation reflects Georgia Tech’s leadership in artificial intelligence, as well as the missions of Tech AI and AI4OPT to advance AI-enabled optimization and decision-making for complex, real-world systems.

We’re proud to share that Tech AI’s own Pascal Van Hentenryck, A. Russell Chandler III Chair and Director of Georgia Tech’s AI Hub, will be among the featured speakers—bringing Georgia Tech’s global perspective on building trustworthy, impactful AI systems.

Learn more about the forum: royalsoc.org.au/events/rsnsw-and-learned-academies-forum-2025

Combining Technologies for Real-World Results

Van Hentenryck introduced a series of foundational approaches—such as primal and dual optimization proxies, predict-then-optimize strategies, self-supervised learning, and deep multi-stage policies—that enable AI systems to operate effectively and responsibly in high-stakes, real-time environments. These frameworks demonstrate the power of integrating AI with domain-specific reasoning to achieve results unattainable by either field alone.

“This is not just about building smarter algorithms,” Van Hentenryck said. “It’s about designing AI that can adapt, learn, and optimize under uncertainty—across supply chains, energy systems, and manufacturing networks.”

Grounded in Real-World Impact

The keynote aligned directly with the MIM 2025 focus on logistics and production systems. Drawing from recent work in supply chain optimization and smart manufacturing, Van Hentenryck emphasized how AI4OPT’s research is already generating measurable impact in industry.

MIM 2025, organized by NTNU’s Production Management Research Group and supported by MHI and CICMHE, featured more than 40 experts delivering keynotes, presenting research, and leading breakout sessions across topics in modeling, control, and decision-making in manufacturing and logistics.

About Tech AI

Tech AI is Georgia Tech’s strategic initiative to lead in the development and application of artificial intelligence across disciplines and industries. Serving as a unifying platform for AI research, education, and collaboration, Tech AI connects researchers, industry, and government partners to drive responsible innovation in areas such as healthcare, mobility, energy, sustainability, and education. Director of Tech AI, Pascal Van Hentenryck helps guide the institute’s research vision and strategic alignment across Georgia Tech’s AI portfolio. Learn more at ai.gatech.edu.

About AI4OPT

The AI Institute for Advances in Optimization (AI4OPT) is one of the National Science Foundation’s flagship AI Institutes and is led by Georgia Tech. The institute brings together experts in artificial intelligence, optimization, and control to tackle grand challenges in supply chains, transportation, and energy systems.

AI4OPT is one of several NSF-funded AI institutes housed within Tech AI’s collaborative framework, enabling cross-disciplinary research with real-world outcomes. Learn more at ai4opt.org.

Now returning for a second year, the Research Collaboration Forum (RCF) is a part of Georgia Tech’s broader Research Collaboration Initiative. By deepening ties with HBCUs and other minority-serving institutions (MSIs), the initiative works to build a research ecosystem capable of sharing expertise and resources essential to tackling global challenges.

Read the full story here.

The tool, known as PROPEL, combines machine learning with optimization techniques to help manufacturers make better decisions in less time. It was created by researchers at the NSF AI Institute for Advances in Optimization, or AI4OPT, based at Georgia Tech under Tech AI (the AI Hub at Georgia Tech).

The technology is already being tested on real-world supply chain data provided by Kinaxis, a Canada-based company that supplies planning software to global manufacturers in industries ranging from automotive to consumer goods.

Vahid Eghbal Akhlaghi, senior research scientist at Kinaxis and former postdoctoral fellow at AI4OPT and the H. Milton Stewart School of Industrial and Systems Engineering (ISyE) at Georgia Tech, said, “Our industry partner has been instrumental in shaping PROPEL’s capabilities. By validating the approach with real operational data, we ensured it addresses true bottlenecks in supply chain planning.”

"PROPEL represents a leap forward in how we tackle massive, complex planning problems," said Pascal Van Hentenryck, lead researcher, the director of Tech AI and the NSF AI4OPT Institute, and the A. Russell Chandler III Chair and Professor at Georgia Tech with appointments in the colleges of engineering and computing. "By combining supervised and reinforcement learning, we can make near-optimal industrial-scale decisions, an order of magnitude faster."

Traditional supply chain planning problems are typically solved using mathematical models that require immense computing power—often too much to meet real-time business needs. PROPEL, short for Predict-Relax-Optimize using LEarning, reduces this burden by teaching the AI model to first eliminate irrelevant decisions and then fine-tune the solution to meet quality standards.

Reza Zandehshahvar, one of the paper’s co-authors and postdoctoral fellow with the NSF AI4OPT and the H. Milton Stewart School of Industrial and Systems Engineering (ISyE) at Georgia Tech, said the breakthrough lies not just in the AI algorithms but in how they're trained and deployed at scale.

“Many AI models struggle when applied to problems with millions of variables. PROPEL was built from the ground up to handle industrial complexity, not just academic examples,” Zandehshahvar said. “We’re seeing real improvements in both solution speed and quality.”

 In trials using Kinaxis’ historical industrial data, PROPEL achieved an 88% reduction in the time needed to find a high-quality plan and improved solution accuracy by more than 60% compared to conventional methods.

While many AI methods in supply chain rely on simulated data or simplified models, PROPEL’s performance has been validated using real-world scenarios, ensuring its reliability in high-stakes operational settings.

The Georgia Tech team says PROPEL could benefit industries that manage large, multi-tiered production networks, including pharmaceuticals, electronics, and heavy manufacturing. The researchers are now exploring partnerships with additional companies to deploy PROPEL in live environments.

Access the abstract on arXiv.

The Institute is one of only four U.S. universities featured in the report, joining Auburn University, Babson College, and the University of North Carolina at Chapel Hill.

“AI isn’t a single system or application—it’s a new foundation for how we work, teach, and learn,” said Leo Howell, Georgia Tech’s chief information security officer. “Our goal is to expose people to as many tools as possible, creating an ‘AI for All’ strategy that ensures everyone at Georgia Tech can leverage AI to enhance their work and learning experiences.”

Georgia Tech’s approach centers on a “persona-based model,” tailoring AI tools and resources to meet the needs of students, faculty, researchers, and administrators. That personalized approach, according to the report, is what makes Georgia Tech’s efforts both scalable and sustainable.

The white paper also emphasizes the importance of industry partnerships in Georgia Tech’s strategy. Through collaborations with Microsoft, OpenAI, and NVIDIA, the Institute is deploying advanced AI technologies while preparing students for the demands of an AI-driven workforce.

Georgia Tech’s success lies in its flexibility, the report notes. The Institute tests AI tools through targeted pilots, gathers user feedback, and rapidly iterates to improve outcomes. This adaptive mindset is recommended as a best practice for other institutions navigating their own AI transformation.

In partnership with Panama’s National Secretariat of Science, Technology and Innovation (Secretaría Nacional de Ciencia, Tecnología e Innovación, or SENACYT) and Georgia Tech Panama, Tech AI the AI Hub at Georgia Tech co-led a series of multisectoral workshops in Panama City on July 7–8. The initiative convened voices from government, academia, civil society, and the private sector to co-create an ethical, inclusive and forward-looking roadmap for AI in Panama.

We’re moving forward with one of the most exciting and important processes for Panama’s future: the development of our National Artificial Intelligence Strategy,” said Franklin A. Morales, Head of International Technical Cooperation Panama's Secretariat for Science, Technology and Innovation at SENACY, in a public statement. “Georgia Tech’s expertise is helping us shape a strategy that’s both ambitious and grounded in global best practices.

 The workshops were facilitated by Pascal Van Hentenryck, Director of Tech AI, the AI Hub at Georgia Tech and the NSF-funded AI Institute for Advances in Optimization (AI4OPT), and Tim Brown, Academic Program Director for AI at Georgia Tech Professional Education. Through interactive working groups, participants assessed Panama’s AI landscape, identified key challenges and opportunities, and helped lay the foundation for long-term national impact.

 In a public statement, Van Hentenryck noted:

We had the honor to spend three days in Panama working on their National AI Strategy with SENACYT, Georgia Tech Panama, and so many stakeholders who contributed their expertise, talent, and time. More to come, obviously. And thank you to the teams at SENACYT, Georgia Tech Panama, and Tech AI at Georgia Tech for an amazing organization.

SENACYT’s vision for Panama’s AI future emphasizes the role of technology in advancing opportunity and improving lives. “The future is not something we wait for—it’s something we build together,” Morales added in a separate public statement.

Additional contributions from leaders across Panama’s innovation ecosystem emphasized the importance of developing homegrown talent, applying AI in high-impact sectors like health and education, and serving as a regional testbed for responsible AI solutions.

 “This goes beyond technology. It’s about how we use artificial intelligence to improve people’s lives, make our systems more efficient, and elevate Panamanian talent,” shared a representative from Escala Latam. “We have a big opportunity: to train local talent, to scale responsible solutions, and to build, from Panama, solutions with global impact.”

 The initiative reflects Georgia Tech’s broader commitment to advancing AI as a public good.

 Through Tech AI and partnerships like this one, the Institute helps governments, industries, and communities around the world design AI strategies that are technically sound, globally relevant, and locally empowering.

“Artificial intelligence has been identified by SENACYT as a critical and emerging technology that requires urgent action to maximize its impact on the country’s economy, innovation capacity, and competitiveness,” said Eduardo Ortega Barría, National Secretary of Science, Technology and Innovation. “That’s why the National AI Strategy we are developing prioritizes broad and participatory reflection—this is a crucial step toward building a shared vision.”

As nations worldwide navigate the rise of artificial intelligence, Georgia Tech stands at the forefront, helping build AI strategies that are not only technically advanced but fundamentally human-centered.

GET INVOVLED

The public is also invited to shape the strategy. SENACYT launched a National Artificial Intelligence Survey—available through July 31 via www.SENACYT.gob.pa; SURVEY and SENACYT’s social media—to collect ideas, questions, and concerns from residents across Panama. (The survey includes 16 questions and is open to all residents of Panama—both nationals and foreigners. Its purpose is to gather perceptions, concerns, and opportunities to be considered in the national strategy. The survey will remain open until July 31, 2025).

About Tech AI

Tech AI is Georgia Tech’s interdisciplinary AI research and policy hub, bringing together expertise in optimization, robotics, ethics, education, and public-sector applications. With a mission to advance AI for social good, Tech AI helps partners across the globe design and deploy trustworthy, scalable AI systems.

About SENACYT

The National Secretariat of Science, Technology and Innovation (SENACYT) is an autonomous institution whose mission is to make science and technology tools for the sustainable development of Panama. Our projects and programs focus on advancing the country’s scientific and technological capabilities to close inequality gaps and promote equitable development that improves quality of life for all Panamanians.

Leading up to the main event, Tech AI, the AI Hub at Georgia Tech, partnered with OpenAI to host two standout events on March 25: the OpenAI Forum and Sora Shorts. These programs explored the rapidly evolving landscape of generative AI and creativity, offering a preview of the transformative work unfolding both at the Institute and across the globe.

OpenAI Academy and Sora Shorts

The OpenAI Academy gave participants hands-on experience with the latest AI tools and methods. The workshop provided a deep dive into how generative AI can be applied across sectors.

Simultaneously, the Sora Shorts series spotlighted creative pioneers integrating AI into storytelling and design. Featured speakers included:

• Mark Riedl, professor at Georgia Tech, who discussed the intersection of AI and storytelling and its impact on narrative innovation;
• Minne Atairu, AI artist and researcher at Columbia University, who explored generative art and the evolving role of AI in creative disciplines;
• Michaela Ternasky-Holland, Emmy Award-winning director, who offered insights into AI’s potential to reshape the future of filmmaking;
• Nik Kleverov, creative director and entrepreneur, who focused on AI's capacity to inspire design and entrepreneurship;
• Ellie Foumbi, filmmaker and member of the Directors Guild of America, who reflected on how AI tools are influencing storytelling and visual production.

Gabe Nixon, a fourth-year student at Georgia Tech, shared how these two events quickly reshaped his career ambitions. Initially on a Ph.D. track aiming for NASA, Nixon pivoted toward startups and AI innovation. After attending the OpenAI Academy, he began building his first AI-powered app, TITAN, during Tech AI Fest. Nixon's experience reflects a broader student interest in harnessing AI to fuel interdisciplinary breakthroughs.

Highlights Included:

Tech AI Fest welcomed AI experts and thought leaders across domains. Speakers included:

• Sen. John Albers, Georgia state senator, who spoke about crafting ethical legislation to govern AI innovation;
• Manuela Veloso, head of AI research at JPMorganChase and former AI head at Carnegie Mellon University, who discussed AI's role in finance and interdisciplinary collaboration;
• Sophia Velastegui, former Microsoft executive, who highlighted AI’s transformative power in solving complex industry problems;
• Konstantin Cvetanov, senior solution architect at NVIDIA, leading the adoption of enterprise AI and generative AI solutions across North America;
• Srinivas Aluru, professor at Georgia Tech, who explored AI's intersection with scientific computing and systems modeling;
• Sudheer Chava, professor at Georgia Tech, who discussed machine learning in financial markets and risk management;
• Yongsheng Chen, professor at Georgia Tech, who presented on AI in agriculture;
• Frank Dellaert, professor at Georgia Tech and CEO of Verdant Robotics, who shared insights into AI-driven autonomous systems and robotics;
• Ashok Goel, professor at Georgia Tech and director of the National Science Foundation AI Institute for Adult Learning and Online Education (AI-ALOE), who focused on AI for education and personalized learning.

Additional speakers included:

• Vijay Ganesh, associate professor at Georgia Tech, on real-time machine learning applications;
• David Joyner, executive director of the Online Master of Science in Computer Science program at Georgia Tech, on scalable AI-powered personalized education;
• Kamran Paynabar, associate professor at Georgia Tech, on AI-enabled optimization in global supply chains;
• Christopher J. Rozell, professor at Georgia Tech, on the role of AI in neuroscience and brain modeling;
• Suresh Marru, associate professor at Georgia Tech, on AI-enhanced cyberinfrastructure for science;
• Bob Friday, chief scientist at Juniper Networks, on AI's impact on networking and cybersecurity;
• Jeffrey Young, principal investigator at Georgia Tech’s Center for Scientific Software Engineering, who discussed open-source frameworks and ethical software development for AI.

Keynote: AI as a Global Force

A standout moment was the keynote from Pascal Van Hentenryck, director of Tech AI and professor in Georgia Tech’s H. Milton Stewart School of Industrial and Systems Engineering. He emphasized that AI's true potential lies in collaboration across academia, industry, and government.

“Artificial intelligence is not just a tool — it’s a revolution,” Van Hentenryck said. “But for it to be truly transformative, we need to come together as a global community to innovate responsibly. At Georgia Tech, we are proud to be at the forefront of this revolution, driving innovation and solving global challenges.”

Looking Ahead: Tech AI Career Fair

Building on the success of Tech AI Fest 2025, Tech AI will host a career fair later this year. The event will connect students, professionals, and companies to explore workforce opportunities in AI and emerging technologies.

“We’re excited about the upcoming Career Fair,” said Tim Brown, Tech AI’s Director of Professional Education and organizer of the career fair. “It will provide a platform for companies to engage with top talent, and for students to discover exciting careers in AI.”

A Lasting Impact

Tech AI Fest marked a defining moment for Georgia Tech’s role in shaping the future of artificial intelligence. From hands-on workshops to thought-provoking discussions on ethics, creativity, and policy, the event created space for new ideas and global partnerships.

As Georgia Tech continues to lead in AI research, education, and collaboration, Tech AI Fest demonstrated what’s possible when visionary thinkers come together to build a better, smarter future.

For more information about Tech AI and upcoming events, visit tech.ai.gatech.edu.

Jill Watson not only answers student questions with high accuracy. It also improves teaching presence and correlates with better academic performance. Researchers believe this is the first documented instance of a chatbot enhancing teaching presence in online learning for adult students.

How Jill Watson Shaped Intelligent Teaching Assistants

First introduced in 2016 using IBM’s Watson platform, Jill Watson was the first AI-powered teaching assistant deployed in real classes. It began by responding to student questions on discussion forums like Piazza using course syllabi and a curated knowledge base of past Q&As. Widely covered by major media outlets including The Chronicle of Higher Education, The Wall Street Journal, and The New York Times, the original Jill pioneered new territory in AI-supported learning.

Subsequent iterations addressed early biases in the training data and transitioned to more flexible platforms like Google’s BERT in 2019, allowing Jill to work across learning management systems such as EdStem and Canvas. With the rise of generative AI, the latest version now uses ChatGPT to engage in extended, context-rich dialogue with students using information drawn directly from courseware, textbooks, video transcripts, and more.

Future of Personalized, AI-Powered Learning

Designed around the Community of Inquiry (CoI) framework, Jill Watson aims to enhance “teaching presence,” one of three key factors in effective online learning, alongside cognitive and social presence. Teaching presence includes both the design of course materials and facilitation of instruction. Jill supports this by providing accurate, personalized answers while reinforcing the structure and goals of the course.

The system architecture includes a preprocessed knowledge base, a MongoDB-powered memory for storing conversation history, and a pipeline that classifies questions, retrieves contextually relevant content, and moderates responses. Jill is built to avoid generating harmful content and only responds when sufficient verified course material is available.

Field-Tested in Georgia and Beyond

The first AI-powered teaching assistant was developed for Georgia Tech’s Online Master of Science in Computer Science (OMSCS) program. By fall 2023, Jill Watson was deployed in Georgia Tech’s OMSCS artificial intelligence course, serving more than 600 students, as well as in an English course at Wiregrass Georgia Technical College, part of the Technical College System of Georgia (TCSG).

A controlled A/B experiment in the OMSCS course allowed researchers to compare outcomes between students with and without access to Jill Watson, even though all students could use ChatGPT. The findings are striking:

• Jill Watson’s accuracy on synthetic test sets ranged from 75% to 97%, depending on the content source. It consistently outperformed OpenAI’s Assistant, which scored around 30%.
• Students with access to Jill Watson showed stronger perceptions of teaching presence, particularly in course design and organization, as well as higher social presence.
• Academic performance also improved slightly: students with Jill saw more A grades (66% vs. 62%) and fewer C grades (3% vs. 7%).

A Smarter, Safer Chatbot

While Jill Watson uses ChatGPT for natural language generation, it restricts outputs to validated course material and verifies each response using textual entailment. According to a study by Taneja et al. (2024), Jill not only delivers more accurate answers than OpenAI’s Assistant but also avoids producing confusing or harmful content at significantly lower rates.

Compared to OpenAI’s Assistant, Jill Watson (ChatGPT) not only achieves higher accuracy but also produces confusing or harmful content at significantly lower rates. Jill Watson answers correctly 78.7% of the time, with only 2.7% of its errors categorized as harmful and 54.0% as confusing. In contrast, OpenAI’s Assistant demonstrates a much lower accuracy of 30.7%, with harmful failures occurring 14.4% of the time and confusing failures rising to 69.2%. Additionally, Jill Watson has a lower retrieval failure rate of 43.2%, compared to 68.3% for the OpenAI Assistant.

What’s Next for Jill

The team plans to expand testing across introductory computing courses at Georgia Tech and technical colleges. They also aim to explore Jill Watson’s potential to improve cognitive presence, particularly critical thinking and concept application. Although quantitative results for cognitive presence are still inconclusive, anecdotal feedback from students has been positive. One OMSCS student wrote:

“The Jill Watson upgrade is a leap forward. With persistent prompting I managed to coax it from explicit knowledge to tacit knowledge. Kudos to the team!”

The researchers also expect Jill to reduce instructional workload by handling routine questions and enabling more focus on complex student needs.

Additionally, AI-ALOE is collaborating with the publishing company John Wiley & Sons, Inc., to develop a Jill Watson virtual teaching assistant for one of their courses, with the instructor and university chosen by Wiley. If successful, this initiative could potentially scale to hundreds or even thousands of classes across the country and around the world, transforming the way students interact with course content and receive support.

A Georgia Tech-Led Collaboration

The Jill Watson project is supported by Georgia Tech, the US National Science Foundation’s AI-ALOE Institute (Grants #2112523 and #2247790), and the Bill & Melinda Gates Foundation.

Core team members are Saptrishi Basu, Jihou Chen, Jake Finnegan, Isaac Lo, JunSoo Park, Ahamad Shapiro and Karan Taneja, under the direction of professor Ashok Goel and Sandeep Kakar. The team works under Beyond Question LLC, an AI-based educational technology startup.

In a move set to transform the field of archival management, Heritage Werks has entered into a groundbreaking partnership with Tech AI, the AI hub at Georgia Tech. This collaboration aims to revolutionize the cataloging, access, and preservation of historical collections, setting new standards for digital asset management through advanced artificial intelligence (AI).

Traditional archives often face challenges related to scale, accessibility, and context. Tech AI is addressing these issues by leveraging cutting-edge AI technologies such as machine learning, natural language processing, and computer vision. These advancements enhance the accessibility, organization, and long-term digital preservation of valuable historical collections.

Through this partnership, Tech AI is strategically developing advanced AI models that enable multimodal content integration, allowing users to seamlessly search and interact with content. By aligning technical innovation with strategic goals, this type of collaboration ensures that historical content remains accessible, relevant, and valuable in the digital age, reinforcing Tech AI's leadership in AI-driven knowledge preservation.

Further fueling this innovation is Heritage Werks' acquisition of NetX, a global leader in digital asset management (DAM). This acquisition integrates NetX’s advanced DAM technology with Heritage Werks’ AI-driven solutions, enhancing archival discovery, metadata enrichment, and strategic insights for a wide range of industries.

“Partnering with Heritage Werks is an incredible opportunity to apply Georgia Tech’s cutting-edge AI research to real-world challenges in archival management,” said Pascal Van Hentenryck,, A. Russell Chandler III Chair and professor, and the director of both Tech AI and the NSF Artificial Intelligence Institute for Advances in Optimization (NSF AI4OPT). “We’re not only preserving history but are also reimagining how it can be experienced.”

By harnessing the power of AI, this partnership enables organizations to make their historical collections more discoverable, engaging, and valuable in the digital age.

As the A. Russell Chandler III Chair and professor in the H. Milton Stewart School of Industrial and Systems Engineering (ISyE), Van Hentenryck shared insights on how artificial intelligence is transforming supply chain systems—making them more efficient, adaptive, and resilient.

In the panel session titled “AI and Beyond: Embracing Digital Transformation in Logistics,” Van Hentenryck joined leaders from The Home Depot, Havertys Furniture, and TOTO USA to discuss how organizations are leveraging AI and other emerging technologies to meet the evolving demands of logistics.

Van Hentenryck also spotlighted Georgia Tech’s leadership in developing responsible and scalable AI solutions that address real-world challenges in mobility, supply chains, and infrastructure.

Tech AI bridges cutting-edge research with practical applications, driving advancements in energy, healthcare, transportation, supply chains, and national security. “Through Tech AI, Georgia Tech is redefining the pathway from academic research to tangible societal benefits,” said Pascal Van Hentenryck, director of Tech AI.

Built on four strategic pillars — applied research, industry partnerships, AI engineering, and workforce development — Tech AI fosters responsible, rigorously tested AI technologies, preparing the next generation of AI innovators. The initiative also leverages Georgia Tech’s NSF-funded AI Institutes and Interdisciplinary Research Institutes, positioning the university as a national AI hub.

Happening now at Georgia Tech, Tech AI Fest highlights the initiative’s impact with hands-on demos, research spotlights, and expert panels. Learn more or explore partnership opportunities at tech.ai.gatech.edu.

The event was designed to provide legislators with a comprehensive understanding of how AI is reshaping key sectors, including energy, manufacturing, education and cybersecurity. Georgia Tech’s prominent role in AI research and application was highlighted through contributions from its leading faculty and research experts.

Tim Lieuwen, interim executive vice president for Research at Georgia Tech, opened the workshop, amplifying the strategic importance of AI for Georgia’s economic development and infrastructure resilience. Pascal Van Hentenryck, director of the Tech AI Hub and the NSF AI4OPT Institute, followed with a presentation on AI advancements and their implications for the state.

A significant portion of the workshop focused on AI’s impact on energy infrastructure. Lieuwen returned to discuss how AI is enhancing energy efficiency and supporting Georgia’s transition to smarter, more resilient energy systems. This session highlighted AI’s role in driving sustainable energy solutions.

The conversation then shifted to manufacturing, with Tom Kurfess, chief manufacturing officer at Georgia Tech, detailing how AI-driven innovations are optimizing production processes and revolutionizing industry practices. His insights described a future where AI maintains Georgia’s competitiveness in the manufacturing sector.

Cybersecurity and data privacy were other focal points. Michael Barker from Georgia Tech’s Manufacturing Extension Program addressed the challenges and opportunities surrounding AI-driven cybersecurity solutions. His presentation touched on data privacy and compliance with public information regulations.

The educational landscape also took center stage as Steve Harmon from Georgia Tech’s College of Lifelong Learning explored the ways AI is reshaping learning experiences. Harmon highlighted AI’s potential to deliver personalized education and better prepare students for a rapidly evolving workforce.

Donna Ennis, interim associate vice president for community-based engagement and co-director of Georgia AIM, wrapped up the program by presenting a comprehensive overview of state and national AI resources available to foster innovation and collaboration.

This event highlighted the importance of strategic investments and informed policymaking to harness the full potential of AI for Georgia’s future.

Kinaxis, a global leader in supply chain orchestration, and the NSF AI Institute for Advances in Optimization (AI4OPT) at Georgia Tech today announced a  new co-innovation partnership. This partnership will focus on developing scalable artificial intelligence (AI) and optimization solutions to address the growing complexity of global supply chains. AI4OPT operates under Tech AI, Georgia Tech’s AI hub, bringing together interdisciplinary expertise to advance real-world AI applications.

This particular collaboration builds on a multi-year relationship between Kinaxis and Georgia Tech, strengthening their shared commitment to turn academic innovation into real-world supply chain impact. The collaboration will span joint research, real-world applications, thought leadership, guest lectures, and student internships.

“In collaboration with AI4OPT, Kinaxis is exploring how the fusion of machine learning and optimization may bring a step change in capabilities for the next generation of supply chain management systems,” said Pascal Van Hentenryck, the A. Russell Chandler III Chair and professor at Georgia Tech, and director of AI4OPT and Tech AI at Georgia Tech.

Kinaxis’ AI-infused supply chain orchestration platform, Maestro™, combines proprietary technologies and techniques to deliver real-time transparency, agility, and decision-making across the entire supply chain — from multi-year strategic orchestration to last-mile delivery. As global supply chains face increasing disruptions from tariffs, pandemics, extreme weather, and geopolitical events, the Kinaxis–AI4OPT partnership will focus on developing AI-driven strategies to enhance companies’ responsiveness and resilience.

“At Kinaxis, we recognize the vital role that academic research plays in shaping the future of supply chain orchestration,” said Chief Technology Officer Gelu Ticala. “By partnering with world-class institutions like Georgia Tech, we’re closing the gap between AI innovation and implementation, bringing cutting-edge ideas into practice to solve the industry’s most pressing challenges.”

With more than 40 years of supply chain leadership, Kinaxis supports some of the world’s most complex industries, including high-tech, life sciences, industrial, mobility, consumer products, chemical, and oil and gas. Its customers include Unilever, P&G, Ford, Subaru, Lockheed Martin, Raytheon, Ipsen, and Santen.

 

About Kinaxis
Kinaxis is a global leader in modern supply chain orchestration, powering complex global supply chains and supporting the people who manage them, in service of humanity. Our powerful, AI-infused supply chain orchestration platform, Maestro™, combines proprietary technologies and techniques that provide full transparency and agility across the entire supply chain — from multi-year strategic planning to last-mile delivery. We are trusted by renowned global brands to provide the agility and predictability needed to navigate today’s volatility and disruption. For more news and information, please visit kinaxis.com or follow us on LinkedIn.  

About AI4OPT
The NSF AI Institute for Advances in Optimization (AI4OPT) is one of the 27 National Artificial Intelligence Research Institutes set up by the National Science Foundation to conduct use-inspired research and realize the potential of AI. The AI Institute for Advances in Optimization (AI4OPT) is focused on AI for Engineering and is conducting cutting-edge research at the intersection of learning, optimization, and generative AI to transform decision making at massive scales, driven by applications in supply chains, energy systems, chip design and manufacturing, and sustainable food systems. AI4OPT brings together over 80 faculty and students from Georgia Tech, UC Berkeley, University of Southern California, UC San Diego, Clark Atlanta University, and the University of Texas at Arlington, working together with industrial partners that include Intel, Google, UPS, Ryder, Keysight, Southern Company, and Los Alamos National Laboratory. To learn more, visit ai4opt.org.

About Tech AI
Tech AI is Georgia Tech's hub for artificial intelligence research, education, and responsible deployment. With over $120 million in active AI research funding, including more than $60 million in NSF support for five AI Research Institutes, Tech AI drives innovation through cutting-edge research, industry partnerships, and real-world applications. With over 370 papers published at top AI conferences and workshops, Tech AI is a leader in advancing AI-driven engineering, mobility, and enterprise solutions. Through strategic collaborations, Tech AI bridges the gap between AI research and industry, optimizing supply chains, enhancing cybersecurity, advancing autonomous systems, and transforming healthcare and manufacturing. Committed to workforce development, Tech AI provides AI education across all levels, from K-12 outreach to undergraduate and graduate programs, as well as specialized certifications. These initiatives equip students with hands-on experience, industry exposure, and the technical expertise needed to lead in AI-driven industries. Bringing AI to the world through innovation, collaboration, and partnerships. Visit tech.ai.gatech.edu.

A Hub for AI Conversations

Tech AI Fest 2025 will bring together over 40 experts from top institutions and leading companies, including:

• Academic Institutions: Georgia Tech, Carnegie Mellon University, Harvard University, the University of Texas at Austin, Washington State University, and Columbia University.
• Leading Companies: J.P. Morgan, NVIDIA, Juniper Networks, Microsoft, OpenAI, Bosch USA, Kinaxis, MindsDB, Verdant Technologies, and Dandelion Science Corp.

Event Highlights

• Days 1 – 2 (March 26 – 27) will focus on how AI is being used in industry, government, and research. Sessions will discuss AI's role in technological progress, economic growth, and policy development.
• Day 3 (March 28) will showcase Georgia Tech's AI projects, including groundbreaking research, student presentations, and the launch of the Tech AI Alumni Group to strengthen industry-academic connections.

Commitment to AI Progress

Tech AI Fest 2025 shows Georgia Tech's dedication to advancing AI research, fostering innovation, and building meaningful partnerships across different sectors. The event is a platform for sharing knowledge, networking, and collaboration, putting attendees at the forefront of the AI revolution.

“AI is more than just an academic pursuit; it’s a force that’s reshaping industries, redefining education, and creating solutions for some of the biggest challenges we face today,” said Pascal Van Hentenryck, the A. Russell Chandler III Chair and professor in Georgia Tech’s H. Milton Stewart School of Industrial and Systems Engineering, director of the NSF Artificial Intelligence Institute for Advances in Optimization (AI4OPT), and director of Tech AI.

Registration and Participation

General admission is $25, but Georgia Tech students can attend for free while seats are available. Due to high demand, registration has reached capacity. Interested individuals can join the waiting list by contacting Josh Tullis at josh@corporate.gatech.edu.

For more information, visit the official event page.

About Tech AI

Tech AI is Georgia Tech’s hub for artificial intelligence research, education, and responsible deployment. It drives real-world AI solutions through innovation, collaboration, and industry partnerships. With over $120 million in active AI research funding and more than 370 publications at top AI conferences, Tech AI is ranked No. 5 in the U.S. for AI research and leads the way in AI-driven engineering and applied research. Supported by over $60 million in National Science Foundation funding, Tech AI plays a critical role in developing the next generation of AI leaders through world-class degree programs and specialized certifications. By bridging the gap between research and real-world applications, Tech AI collaborates with industry and government partners to optimize supply chains, enhance cybersecurity, advance autonomous systems, revolutionize healthcare, improve energy efficiency, and drive sustainable manufacturing.

Themed “Customer-Centric Culture,” the event explored how leaders and employees can harness AI for customer engagement. Key topics included: defining AI, guiding workforce adaptation to AI-driven changes, and debunking myths, emphasizing AI's role as a vital tool rather than a threat.

To learn more about the Georgia Department of Human Services, click here.

Their paper dives into the critical role of explainability in AI systems designed to support older adults aging in place. The team emphasizes creating AI explanations that are personalized, collaborative, and user-centered, particularly for older adults and their care partners.

By employing the Research through Design (RtD) methodology, they explored the diverse needs, motivations, and goals of users in the home setting. Their work proposes a shift in the AI research community—moving from algorithm-focused explanations to user-centered, collaborative design approaches. This includes techniques such as Speed Dating studies and Co-Design activities, which engage users directly in the design process, making explanation a shared, iterative task between AI systems and users.

Niharika Mathur, a Ph.D. student in Human-Centered Computing (HCC) at Georgia Tech specializing in Human-Computer Interaction (HCI), specializes in the design of conversational AI systems, such as smart speakers like Google Home. Her research focuses on how these technologies can be better designed to improve human-AI interaction and support everyday tasks.

Tamara Zubatiy, a Postdoctoral Research Associate, is also recognized as part of the 2025 Forbes 30 Under 30 list. She is a researcher at the Everyday Computing Lab, directed by Professor Beth Mynatt, which focuses on technology's role in improving people's daily lives, particularly for older adults and their caregivers.

Beth Mynatt, former Georgia Tech faculty and now Dean of Khoury College of Computer Sciences at Northeastern University, has made significant contributions to the field of Human-Computer Interaction (HCI) and continues to lead transformative research on the design and implementation of technology for everyday tasks.

The team’s research advocates for a fundamental shift in the focus of Explainable AI (XAI) toward the specific requirements of users, thus improving the accessibility and usability of AI systems for aging populations.

For those interested in exploring this work further, the full paper is available via the DOI: https://dl.acm.org/doi/10.1145/3688828.3699640. You can also download the PDF directly here: Read the Full Paper.

Once again, congratulations to Niharika, Tamara, and Beth for this well-deserved recognition of their innovative and impactful research!

The program held at both Georgia Tech and Clark Atlanta University sites, in June, consisted of faculty members from Historically Black Colleges and Universities (HBCU’s) and Minority Serving Institutions (MSI’s) from states including Georgia, California, Texas and Virginia. The three-year program is comprised of courses in artificial intelligence (AI), data science and course design. For Butros, the opportunity has proven to be both useful and beneficial.

“There were people who had Ph.D.’s in computer science and people like me, who had never done any data science or computer programming in Python or Acorn RISC Machine,” said Butros. “Everything was great, and everyone was willing to help each other.”

The Goal of Faculty Training Program

The Faculty Training Program aims to establish a minor or major data science program for each of the participants’ home institutions. Each participant will then set up joint research projects with AI4OPT researchers at Georgia Tech, UC Berkeley and the University of Southern California to eventually host their own data science seminars and workshops.

“The training program not only benefits Georgia Tech. It’s a STEM pipeline for campus communities across the country,” said Pascal Van Hentenryck, director of the Faculty Training Program and AI4OPT. “This program creates a much more diverse and trusting environment, and we are trying to build this pipeline with various organizations, while also gaining the attention of bright-minded students. These students will become role models for other students and then they become faculty. We are fostering this virtuous cycle.”

Before Butros retires from VVC, he plans to be further that cycle of STEM programs by applying for Georgia Tech's Online Master of Science in Analytics (OMS Analytics), and also create a culture of data science research for undergraduate students at VVC.

“A lot of the student I deal with are going into engineering, pre-med and computer science. Nowadays it’s very difficult if you don’t have any research under your belt,” said Butros. “It’s going to be very difficult to expose our students to the latest technology, but we’re trying and that is why programs like the Faculty Training Program are a shining light for us because they are willing to share their facilities and resources.”

About AI4OPT Faulty Training Program

The AI4OPT Faulty Training Program is the brainchild of AI4OPT Director, Pascal Van Hentenryck, A. Russell Chandler III Chair and professor in Georgia Tech’s H. Milton Stewart School of Industrial and Systems Engineering (ISyE) and Dr. Charles Pierre, a professor in the Mathematical Sciences Department at Clark Atlanta University and Advisory Committee Interim Chair. Participants of the program are hosted at Georgia Tech and Clark Atlanta University for the first four weeks where Pierre and his team provide training while AI4OPT researchers visit, give research talks and make connections. After the visit to Georgia Tech, the participants will continue training online for another four weeks to complete the first course. The multi-year collaboration will ultimately give participant basis to start AI and data science programs at their colleges and universities.

For general information about the AI4OPT Faculty Training Program, contact Cami Douglass, AI4OPT executive assistant at 404-894-5953 or via email at camille.douglass@isye.gatech.edu.

About Victor Valley College

The Victor Valley Community College District (VVCCD) is one of 73 community college districts within the California Community College system, the largest educational system in the world, which encompasses 116 community colleges. The VVCCD has for 60 years provided its communities and students with quality and affordable career training, certificates, associate degrees and transfer preparation into four-year colleges or universities through Victor Valley College.

For additional information on the VVCCD, contact Robert Sewell, Director of Marketing and Public Relations at 760-245-4271, Ext. 2395 or via email at robert.sewell@vvc.edu.

To learn more about the AI Institute for Advances in Optimization, visit www.ai4opt.org.

(Writer’s note: This article is part of a series highlighting AI4OPT members, students, education programs and professional development testimonies.

On Tuesday, December 03, 2024, the Senate Study Committee on Artificial Intelligence (AI) finalized 22 recommendations to guide Georgia’s response to AI.

In its eighth and final meeting at the Capitol, the nine-member committee unanimously approved a detailed 185-page report. The document’s key recommendations focus on state and local government, education and workforce development, public safety, healthcare, transparency and accountability, and industry-specific findings for entertainment, agriculture, and manufacturing.

The committee, formed in May 2024, explored both current and future applications of AI, and also aimed to strike a balance between necessary AI regulations and policies that foster innovation and growth, shining a spotlight on AI’s growing significance in various fields.

The committee, chaired by Sen. John Albers (R–Roswell), included Pascal Van Hentenryck, an A. Russell Chandler III Chair and Professor in the H. Milton Stewart School of Industrial and Systems Engineering at Georgia Tech (ISyE), director of the NSF AI Institute for Advances in Optimization (AI4OPT), and director of Tech AI, the AI Hub at Georgia Tech.

“The committee did outstanding work engaging with many stakeholders across the state, learning about AI’s role in key economic sectors, about AI education, the opportunities and dangers of AI, and potential legislation to balance innovation with the well-being of Georgia residents. It was a true privilege to be part of this committee, and the report has already drawn praise around the country,” said Van Hentenryck.

In a statement, Sen. Albers said, “AI has the potential to improve every Georgian’s quality of life, from addressing food security through precision agriculture to enhancing emergency response and advancing personalized education. However, we must balance innovation with safeguards to protect privacy, fairness, and transparency.”

The committee also proposed the formation of a state board for AI and suggested collaborating with other states to establish interstate AI compacts.

Over the course of its work, the committee held numerous meetings featuring testimony from experts in various fields. Van Hentenryck played a pivotal role in these discussions, particularly when he presented on the topic of trustworthy AI for societal impact. 

He emphasized the need for AI systems that not only perform at a high level but also align with ethical standards Van Hentenryck also highlighted Georgia Tech’s commitment to applying AI in real-world scenarios, supported by its extensive research and development efforts.

Breakdown of Committee’s Findings and Recommendations

1. Every state agency should create a clear plan and policy for using AI.
2. Pass laws that regulate AI without blocking innovation, focusing on data privacy and preventing the misuse of deepfakes.
3. Define AI clearly at the state level.
4. Keep updating state laws as AI technology advances.
5. Ensure public organizations track and share the source of their data and AI usage.
6. Require reports on AI tools in use and how they benefit the state.
7. Promote partnerships between the public and private sectors to integrate AI in K-12 schools in Georgia.
8. Support state programs to help workers learn new skills in AI through partnerships with schools.
9. Develop AI education plans for Georgia’s K-12 schools.
10. Create AI strategies for the University System of Georgia and Technical College System of Georgia.
11. Identify ways AI can improve emergency response and management.
12. Make AI tools more accessible to improve healthcare outcomes and efficiency.
13. Study how AI impacts mental health services.
14. Ensure transparency in AI systems used in Georgia.
15. Offer certification for companies that are transparent about their AI practices.
16. Make sure AI systems clearly disclose when they are interacting with people.
17. Make deepfake technology illegal when used to spread misinformation or cause harm.
18. Hold AI products legally responsible, just like physical products.
19. Promote AI systems that include human oversight (human-in-the-hoop and human-on-the-loop).
20. Offer incentives for Georgia-based entertainment projects that use AI.
21. Provide grants to help small farms use AI technology.
22. Encourage collaborations between government, businesses, and universities to drive AI research and workforce development.

The final report of the committee emphasizes AI’s transformative potential in reshaping industries and improving public services, offering a roadmap for the ethical, responsible deployment of AI technologies in Georgia.

“Tech AI is organizing a session on AI and Government during Tech AI Fest in March 2025,” Van Hentenryck said. “We’ve invited Senator Albers to brief the community on the report’s findings and outline the next steps for advancing AI initiatives in Georgia.”

Read more »

Q: What do you believe will be the most significant breakthrough in AI in 2025? 

A: Predicting breakthroughs is inherently difficult, as they often emerge unexpectedly. Most major advancements stem from years of incremental progress and research that suddenly converge into a solution that surprises us with its effectiveness. Usually, these breakthroughs originate in areas that are not yet widely recognized as promising or trending.

This unpredictability highlights the importance of sustained investment in diverse research directions, including high-risk projects and fundamental science. By prioritizing innovation, companies and the U.S. government can help ensure the groundwork is laid for transformative discoveries in AI.

Q: Which industries will experience the greatest transformation due to AI in the next year?  

A: In the coming year, advancements in AI are poised to transform industries across the board, both within and beyond the tech sector. Sectors such as healthcare, retail (custom service), marketing, law, education, entertainment, and many others are increasingly adopting large language models (LLMs) to enhance data analysis and improve user interactions. These models offer capabilities far surpassing traditional machine learning methods, driving a shift toward more efficient and intelligent systems.

Ethical and Societal Impact 

Q: What are the most pressing ethical challenges for AI development and deployment in 2025? 

A: Safety: One of the most critical concerns is ensuring the accuracy and reliability of AI systems, especially in high-stakes scenarios such as providing medical advice.

Privacy: With AI systems, privacy risks are heightened when users share vast amounts of personal data — such as emails, resumes, and meeting transcripts.

Fairness: Language models must be designed to account for diverse cultural backgrounds, values, opinions, and languages—including dialects and individual linguistic styles. 

Q: How do you see AI influencing education and learning in the coming year?

A: AI will significantly impact education. It can expand access to knowledge through personalized learning tools and make educational materials more widely accessible. Integrating AI into K-12 curriculums will raise public awareness and prepare students for the future. However, educators are concerned about misuse, such as students relying on AI to complete assignments without fully understanding the material.

Q: What role will generative AI play in shaping public discourse and creativity in 2025? 

A: I think Joanna Maciejewska's comment has crystallized it: "I want AI to do my laundry and dishes so that I can do art and writing, not for AI to do my art and writing so that I can do my laundry and dishes.

Research and Technology 

Q: What advancements in AI hardware or infrastructure are crucial for 2025?

A: Advancements in AI hardware and infrastructure crucial for 2025 include innovations in GPU and specialized hardware such as TPUs (tensor processing units) or custom AI chips, which can accelerate model training and inference. Equally critical is improving the energy efficiency of these components, as current AI models heavily rely on massive GPU computing and data center infrastructure. 

Q: Which areas of AI research would you say are under-funded or under-explored?

A: Many! While the field sees a high volume of publications, much of the work tends to be surface-level or rushed, with fewer resources dedicated to deep, innovative research. This can lead to the illusion of progress in some areas without truly solving the underlying problems. For instance, despite significant advancements, challenges remain in areas like machine translation. While current systems perform impressively, they often fall short in capturing nuances, cultural context, and idiomatic expressions. Similarly, tools like ChatGPT can assist with writing. However, they still struggle to match a skilled human writer's sophistication, coherence, and creativity. Furthermore, using AI in writing can sometimes result in the loss of personal linguistic style, making outputs less authentic or unique.

Q: How do you predict AI regulations or policies will evolve over the next year? 

A: Over the next year, I anticipate and hope that AI regulations and policies will become more nuanced as policymakers and the public gain a deeper understanding of AI technologies. Ideally, we will see more policymakers, such as U.S. congressional members, with science or engineering backgrounds who can approach AI advancements with a balanced perspective. Such leaders would be better equipped to craft thoughtful regulations addressing privacy, copyright, and bias while avoiding stifling innovation through over-regulation.

Additionally, I hope for a concerted effort to enhance AI literacy among the general public through media, educational initiatives, and public discourse. Greater familiarity with AI technologies can lead to more informed and constructive opinions, helping shape regulations that reflect societal values and priorities. This combination of knowledgeable policymakers and an AI-aware public could foster a regulatory environment that supports innovation while ensuring ethical and

Vision and Advice 

Q: What emerging technologies or approaches in AI excite you the most for 2025?

A: For 2025, I'm most excited about:

• AI-driven personalization: AI adapting to individual language styles, cultural backgrounds, personal knowledge, and real-time context.
• Multilingual and multi-modal models: Enhancing non-English language performance and integrating diverse data types seamlessly.
• Domain-specific foundation models: Specialized models for law, biology, and material science to accelerate breakthroughs.

Additionally, improving large language models in safety, privacy, robustness, efficiency, and better training techniques remains a fundamental focus for better overall performance.

Q: What advice would you offer to students or researchers entering AI in 2025? 

A: My advice for students and researchers entering AI in 2025 is to focus on what truly excites you. Take it step by step—read papers, deepen your knowledge, and stay grounded to avoid feeling overwhelmed. While staying informed about trends is important, aim to be an early adopter of emerging ideas or work on solving long-standing, challenging problems. By pursuing your passion, prioritizing originality, and leveraging your unique strengths, you can forge your path and make a meaningful impact in the field.

This initiative, part of the NSF ExpandAI program, aims to boost minority-serving institution participation in AI research, education, and workforce development through capacity-building projects and partnerships within the NSF-led National AI Research Institutes ecosystem.

Building an AI community is no easy feat, but the CAU-GT/AI4OPT collaboration is prepared to meet it. The project, known as AIHUB@CAU, will be led by principal investigator Charles B. Pierre, associate professor in CAU’s Department of Mathematical Sciences.

"The mission of the grant aligns with the AI4OPT Faculty Training Program, which focuses on strategies to increase minority participation in AI research programs from HBCUs to other minority-serving institutions," said Pierre, who also leads the Educational and Diversity Initiatives at AI4OPT. "Our goal is to ensure diverse representation in the AI field."

The collaboration will use existing educational resources and infrastructure to build centers of excellence in AI and a community of empowered Black AI researchers. 

"We anticipate challenges in developing coursework, including finding qualified industry professionals to teach and preparing academic professors unfamiliar with AI," Pierre said. "Our aim is to establish Ph.D. programs at CAU and position the university as a hub for AI training, addressing these issues head-on."

AIHUB@CAU will integrate industry partnerships to accelerate curriculum development and real-world applications. It expands AI education beyond machine learning to encompass decision-making and applications in fields like business analytics, cyber-physical security, and operations research.

Partially funded through NSF's Louis Stokes Alliances for Minority Participation program, this award underscores NSF's commitment to diversity in STEM fields through impactful educational and research initiatives.

"Establishing programs at institutions like Clark Atlanta University and AI4OPT at Georgia Tech provides students with essential resources and tools to succeed in this ever-evolving field," Pierre noted.

Goals and Structure of the AI Education Program

Main Goals of Creating AI Courses at the Undergraduate and Graduate Levels:

• Close the gap of AI graduates from HBCUs at undergraduate and graduate levels.
• Prepare HBCU students for the AI workforce.
• Align with the vision of AI4OPT at Georgia Tech to "democratize access to AI education."

Impact on Students' Career Prospects and the AI Research Community:

• Undergraduate courses and programs will prepare students for entry-level positions in the field.
• Graduate courses and programs will prepare students for research and participation in the AI research community.

Role and Contribution:

• AI4OPT at Georgia Tech will assist CAU with the development of both undergraduate and graduate courses and programs.
• Offer research opportunities to CAU students at the undergraduate and graduate levels.
• AI4OPT at Georgia Tech will be a partner in the established AI Research Hub.

Support for Development of MS and Ph.D. Courses:

• Use current courses at Georgia Tech as a template.
• Use the courses offered through the Faculty Training Program (FTP) of AI4OPT.

Foundational AI Courses:

• Courses already taught by CAU faculty in the AI4OPT FTP.
• Courses available at Georgia Tech.
• New courses to be developed by AIHUB@CAU based on Intel material, focusing on computer vision and natural language processing.
• Courses in applied optimization developed by AI4OPT.
• New use-inspired AI courses teaching applications of AI in various domains, such as supply chains, security, chemistry, and manufacturing.

Research Opportunities:

• The Undergraduate Research Program (URP) will provide students with early exposure to AI research, including summer internships at Georgia Tech and other AI4OPT sites.
• The graduate programs will include an 18-month non-thesis master's degree with a summer internship and capstone project, and a two-year thesis master's degree supported by a six-month research project.

Structure of the New Master in AI Program:

• Courses in five categories to support the master’s program:
  1. Existing courses at CAU taught in the AI4OPT FTP.
  2. Courses available at Georgia Tech.
  3. New courses based on Intel material.
  4. Applied optimization courses developed by AI4OPT.
  5. New courses developed by AIHUB@CAU focusing on AI applications in various domains.

Collaborations and Internships:

• Joint supervision of research projects by CAU and AI4OPT faculty.
• Summer internships starting in 2026.
• Capstone projects facilitated by Georgia Tech and industrial partners.

About AI4OPT

The Artificial Intelligence (AI) Research Institute for Advances in Optimization, or AI4OPT, aims to deliver a paradigm shift in automated decision-making at massive scales by fusing AI and Mathematical Optimization (MO) to achieve breakthroughs that neither field can achieve independently. The Institute is driven by societal challenges in energy, logistics and supply chains, resilience and sustainability, and circuit design and control. To address the widening gap in job opportunities, the Institute delivers an innovative longitudinal education and workforce development program.

About Georgia Tech

The Georgia Institute of Technology, or Georgia Tech, is a top 10 public research university developing leaders who advance technology and improve the human condition. The Institute offers business, computing, design, engineering, liberal arts, and sciences degrees. Its nearly 40,000 students, representing 50 states and 149 countries, study at the main campus in Atlanta, at international campuses, and through distance and online learning. As a leading technological university, Georgia Tech is an engine of economic development for Georgia, the Southeast, and the nation, conducting more than $1 billion in research annually for government, industry, and society.

About Clark Atlanta University

Clark Atlanta University was formed with the consolidation of Atlanta University and Clark College, both of which hold unique places in the annals of African American history. Atlanta University, established in 1865 by the American Missionary Association, was the nation’s first institution to award graduate degrees to African Americans. CAU is also the largest of the 37-member UNCF institutions. CAU, established four years later in 1869, was the nation’s first four-year liberal arts college to serve a primarily African American student population. Today, with over 4,000 students, CAU is the largest of the four institutions (CAU, Morehouse College, Spelman College, and Morehouse School of Medicine) that comprise the Atlanta University Center Consortium.

About National Science Foundation

The U.S. National Science Foundation propels the nation forward by advancing fundamental research in all fields of science and engineering. NSF supports research and people by providing facilities, instruments and funding to support their ingenuity and sustain the U.S. as a global leader in research and innovation. With a fiscal year 2023 budget of $9.5 billion, NSF funds reach all 50 states through grants to nearly 2,000 colleges, universities and institutions. Each year, NSF receives more than 40,000 competitive proposals and makes about 11,000 new awards. Those awards include support for cooperative research with industry, Arctic and Antarctic research and operations, and U.S. participation in international scientific efforts.

PSR is a global leader in analytical solutions for the energy sector, providing innovative technical consultancy services and state-of-the-art power systems planning software. Their tools are used for detailed modeling of entire countries or regions and are utilized in over 70 countries. Together with AI4OPT, they aim to leverage advancements in AI and mathematical optimization to address pressing energy transformations in Latin America and the U.S.

Latin America boasts abundant renewable energy resources, especially hydropower, leading to one of the largest shares of renewables in its energy mix. However, expanding renewable energy capacity in Latin America and the U.S. to meet decarbonization goals will require system operational advances and new technologies that can adapt to current needs.

One focus of this collaboration will be studying how to efficiently incorporate pumped storage into the resource mix as a solution for long-duration storage. These plants act as large batteries, pumping water to higher reservoirs during low demand periods and generating electricity during high demand with minimal energy loss over time. This technology supports both short-term and long-term energy storage, making it crucial for managing the variability of intermittent renewables like solar and wind.

The complex and large-scale nature of the expansion problem, exacerbated by inherent uncertainty and time-coupled decisions, traditionally requires sophisticated optimization techniques. AI innovations now provide faster solutions and better representations of non-linear dynamics, leading to more cost-effective operations and optimized energy mix selection for the energy transition.

This collaboration plans to use machine learning to enhance power system operators' ability to perform faster security checks and screenings. As renewable energy sources introduce more variability, traditional methods struggle with the increasing number of scenarios needed for grid stability. Machine learning offers a solution by expediting these analyses, supporting the integration of more renewable energy into the system.

About PSR

PSR is a global provider of analytical solutions for the energy sector, spanning from insightful and innovative technical consultancy services to state-of-the-art specialized power systems planning software applied to the detailed modelling of entire countries or regions. Having its products applied in over 70 countries, PSR contributes to the research and development of optimization and data analytics’ tools for guaranteeing a reliable and least-cost operation of power systems, helping the countries achieve their decarbonization targets.

About AI4OPT

The Artificial Intelligence (AI) Research Institute for Advances in Optimization, or AI4OPT, aims to deliver a paradigm shift in automated decision-making at massive scales by fusing AI and Mathematical Optimization (MO) to achieve breakthroughs that neither field can achieve independently. The Institute is driven by societal challenges in energy, logistics and supply chains, resilience and sustainability, and circuit design and control. To address the widening gap in job opportunities, the Institute delivers an innovative longitudinal education and workforce development program.

Developed in collaboration with the NSF AI Research Institute for Advances in Optimization (AI4OPT) and with support from the National Science Foundation’s ExpandAI program, the new project aims to expand AI learning and accessibility, positioning CAU as a leader in AI advancements at historically Black colleges and universities (HBCUs) and beyond.

AIHUB@CAU is dedicated to bridging the gap in AI knowledge and skills for minority students, providing new pathways into one of today’s fastest-growing sectors.

HBCUs are crucial in diversifying the tech sector, producing nearly 50% of Black engineers in the U.S., despite representing only 3% of U.S. higher education institutions, according to the United Negro College Fund and the National Science Foundation.

This initiative highlights the commitment to elevating HBCUs as leaders in AI education and research, creating a lasting effect that will benefit generations of learners and faculty.

AIHUB@CAU builds on a successful collaboration between CAU and AI4OPT, starting with the Faculty Training Program in AI. “We are now in our third cohort of faculty from CAU’s mathematics department, bringing together professors dedicated to making AI accessible and applicable,” said Charles Pierre, co-principal investigator of AI4OPT and lead PI for AIHUB@CAU. “AIHUB@CAU strengthens our partnership, expanding its reach across the CAU community.”

Francis Williams, CAU’s vice president of research and sponsored programs, emphasized the broader potential of the partnership. “Through new programs at both the undergraduate and graduate levels, AIHUB@CAU will be instrumental in training the next generation of AI professionals. Increasing minority representation in AI will ensure that we have a diverse workforce prepared to shape tomorrow’s AI-driven economy.”

Empowering Local Communities with a Global Vision

Focusing on AI literacy and community impact, AIHUB@CAU connects academic instruction with real-world applications, closing the gap between education and industry. The center’s mission aligns closely with CAU and AI4OPT’s shared goals of bringing AI resources to traditionally underrepresented areas in technology. The hub will offer workshops, hands-on learning, and foster collaboration and partnerships.

Pascal Van Hentenryck, director of AI4OPT and Tech AI at Georgia Tech, expressed the significance of the milestone: “We’re grateful to support this initiative and honored to witness the start of a powerful movement for diversity in AI,” he said. “AIHUB@CAU is not only about making resources accessible; it’s about empowering students and faculty with the tools to lead and innovate.”

Creating a Blueprint for Inclusive AI Progress

Supported by NSF’s ExpandAI initiative, which promotes the spread of AI expertise to underrepresented institutions, AIHUB@CAU is poised to become a model for similar programs nationwide. Georgia-Ann Klutke, NSF’s program director, highlighted the broader significance: “This is a significant step not just for CAU but for all institutions looking to increase engagement in AI. AIHUB@CAU is a prototype for inclusive AI education and innovation.”

As AI continues to shape the future of global industries, initiatives like AIHUB@CAU are vital for building a diverse talent pipeline in the field. Clark Atlanta University is leading the way in addressing representation gaps in technology, helping to create a future where diverse voices drive AI advancements across sectors and communities. With its commitment to equitable AI education, CAU is paving the way for a more inclusive AI ecosystem—one that opens new opportunities for HBCU students and drives meaningful change.

About AI4OPT

The Artificial Intelligence (AI) Research Institute for Advances in Optimization, or AI4OPT, aims to deliver a paradigm shift in automated decision-making at massive scales by fusing AI and Mathematical Optimization (MO) to achieve breakthroughs that neither field can achieve independently. The Institute is driven by societal challenges in energy, logistics and supply chains, resilience and sustainability, and circuit design and control. To address the widening gap in job opportunities, the Institute delivers an innovative longitudinal education and workforce development program.

About Georgia Tech

The Georgia Institute of Technology, or Georgia Tech, is a top 10 public research university developing leaders who advance technology and improve the human condition. The Institute offers business, computing, design, engineering, liberal arts, and sciences degrees. Its nearly 40,000 students, representing 50 states and 149 countries, study at the main campus in Atlanta, at international campuses, and through distance and online learning. As a leading technological university, Georgia Tech is an engine of economic development for Georgia, the Southeast, and the nation, conducting more than $1 billion in research annually for government, industry, and society.

About Clark Atlanta University

Clark Atlanta University was formed with the consolidation of Atlanta University and Clark College, both of which hold unique places in the annals of African American history. Atlanta University, established in 1865 by the American Missionary Association, was the nation’s first institution to award graduate degrees to African Americans. CAU is also the largest of the 37-member UNCF institutions. CAU, established four years later in 1869, was the nation’s first four-year liberal arts college to serve a primarily African American student population. Today, with over 4,000 students, CAU is the largest of the four institutions (CAU, Morehouse College, Spelman College, and Morehouse School of Medicine) that comprise the Atlanta University Center Consortium.

About National Science Foundation

The U.S. National Science Foundation propels the nation forward by advancing fundamental research in all fields of science and engineering. NSF supports research and people by providing facilities, instruments and funding to support their ingenuity and sustain the U.S. as a global leader in research and innovation. With a fiscal year 2023 budget of $9.5 billion, NSF funds reach all 50 states through grants to nearly 2,000 colleges, universities and institutions. Each year, NSF receives more than 40,000 competitive proposals and makes about 11,000 new awards. Those awards include support for cooperative research with industry, Arctic and Antarctic research and operations, and U.S. participation in international scientific efforts.

About NSF ExpandAI

The National Science Foundation Expanding AI Innovation through Capacity Building and Partnerships (ExpandAI) program aims to significantly broaden participation in AI research, education, and workforce development through capacity development projects and through partnerships within the National AI Research Institutes ecosystem. The NSF ExpandAI program includes a track for minority serving institutions and AI institutes to propose together new partnerships. ExpandAI program information can be found at the official program page.

The National Science Foundation and its partners support the continued growth of a broad and diverse interdisciplinary research community for the advancement of AI and AI-powered innovation, providing a unique opportunity to broadly promote the NSF vision and core values, especially inclusion and collaboration. 

Speakers hailed from a range of industries and disciplines, illustrating the diversity of applications and challenges in integrating AI and optimization. Attendees were immersed in cutting-edge research and real-world applications of these technologies.

Digital Transformation in Asset Management

Geraldo Rochocz, chief technology officer at Radix Engineering, discussed the company’s global shift toward digital transformation. “AI is not a solo play,” Rochocz said, emphasizing the need for collaboration across disciplines. Radix is transitioning from manual tools and spreadsheets to a unified digital platform that will be deployed across more than 50 sites worldwide. Their AI-powered asset management initiative combines AI and non-AI solutions to optimize operations, demonstrating how customized AI solutions can meet industry-specific needs. Radix’s approach reveals that successful AI implementation builds much-needed collaboration in varying industries.

AI Addressing National Security Challenges

Russell Bent, a scientist from Los Alamos National Laboratory, shared how AI is being used to design and control resilient energy systems. He explained that building energy security requires multi-sector, multidisciplinary collaboration to create solutions that balance efficiency, resilience, and adaptability.

Insights from Industry Leaders

Throughout the event, a recurring theme was that AI systems need to be both impactful and trustworthy. Kevin Dalmeijer, AI4OPT managing director, noted, “Leaders across industries have recognized that artificial intelligence will have a major impact on their sector. Multiple speakers talked about seizing the moment to not be left behind.”

Chantal Bisson-Krol, vice president of AI and Machine Learning Solutions at Kinaxis, presented the research the company has been working on in collaboration with AI4OPT. This work has been focused on AI programs which ensure recommendations for supply chain systems align with the company’s real-world business constraints.

Eli Kuperman, corporate relations manager at AI4OPT, emphasized the importance of progress in these areas. “Many companies begin by creating Large Language Models, but improving inferencing layers in models leads to better accuracy and results,” said Kuperman.

Key Takeaways and Applications

TechFest showcased AI’s transformative potential across industries:

• Energy Innovation: ERCOT discussed the growing energy demands of AI computation and the need for efficient energy models to ensure sustainability.
• Streamlining Workflows: VT Industries demonstrated how AI can reduce repetitive tasks, allowing workers to focus on higher-value decision-making.

The Road Ahead

As AI and optimization continue to converge, the insights shared at TechFest 2024 illustrate how collaboration and innovation can unlock new possibilities. Fusing these systems — whether by optimizing industrial assets, national security, or supply chain management — has the potential to reshape industries and solve complex global challenges.

TechFest 2024 showcases AI4OPT's role in advancing research and building collaborations that push the boundaries of AI and optimization, with applications across industries such as healthcare, finance, and energy. The year's event demonstrated how AI-powered optimization is transforming decision-making processes and solving complex, real-world problems.

As part of the global academic team, Georgia Tech is contributing its expertise in systems engineering, optimization, and energy systems integration. 

Pascal Van Hentenryck, the A. Russell Chandler III Chair and Professor at Georgia Tech., the director of the NSF Artificial Intelligence Institute for Advances in Optimization (AI4OPT), and the director of Tech-AI, the AI hub at Georgia Tech, is bringing his expertise to the project, ensuring that the university's research will help shape the future of clean energy.

The EPICS Center's mission is to develop computing, economic, engineering, and policy methods to enable the reliable operation of power grids powered by renewable resources such as wind, solar, and energy storage. By addressing critical challenges like integrating large-scale inverters into the grid, the EPICS Center is advancing strategies for building a net-zero power grid that could serve as a model for global clean energy transformation.

Hughes and his students sought to answer questions about reproduction and food supply, as they worked to add new complexities to the VERA application from different species of trout, circumstances, to changes. According to the Encyclopedia of Life (EOL), an international effort, led by the Smithsonian Institution's National Museum of Natural History, brook trout are found in three types of aquatic environments: rivers, lakes, and marine areas and their living requirements in these environments.

“Originally when we populated the brook trout, we noticed the brown trout shared the same life history and ecological information, but we were able to find enough information from the Encyclopedia of Life to differentiate those species,” said Hughes. “I had my students run through the process of building these components through an instructional-based format by having them manipulate some of the parameters and probabilities.”

VERA was developed by the Design & Intelligence Lab at Georgia Tech in collaboration with EOL. The technology is being used by students as an assisting tool and is publicly accessible. The data being collected from their usage is part of the research conducted at the NSF AI Institute for Adult Learning and Online Education (AI-ALOE).

“Users can jump into our program and conduct ‘what if’ experiments by adjusting simulation parameters. This is our way of providing an accessible and informal learning tool,” said Ashok Goel, director and co-principal Investigator of AI-ALOE and computer science professor at Georgia Tech. “Using VERA as an assessment tool is excellent. These students are using VERA in a way we are not.”

Goel was recently joined by Georgia Tech graduate researcher Andrew Hornback, research scientist Sandeep Kakar, and staff member Daniela Estrada at NGTC to learn more about the work in VERA and challenges Hughes and his students faced while using the application.

“The main struggle is limitation with the EOL and database,” said Hughes. “There are some species that we just can’t find, and sometimes it is glitchy and doesn’t work right away, but it is not insurmountable.”

Another challenge Hughes’ students found was not being able to find what they wanted to complete certain tasks, such as stream and environmental patterns of comparative fish ecosystems.

With that being known, AI-ALOE is working to address these issues and more to build and cater to specific student and teacher needs. At this time, the Design & Intelligence Laboratory is in the process of expanding VERA in the capability of its on-demand agent-based simulation generator, which would enable users to divide components into separate habitats.

“It was very interesting to see the results because antidotally through much research we were able to set up all these relationships and let them run the model, and the results were exactly what we would have hypothesized what they would be given those perimeters,” said Hughes.

The technical college has plans to introduce VERA to another classroom this semester held by Natural Resource Management instructor, Kevin Peyton.

About VERA

Interested in trying out VERA? Create an account at https://vera.cc.gatech.edu/. You can also find VERA’s user guide as well as a step-by-step tutorial at http://epi.vera.cc.gatech.edu/docs/exercise.

About AI-ALOE

The NSF AI Institute for Adult Learning and Online Education (AI-ALOE) is developing an AI-based transformative model for online adult learning through research and data collection.

About NGTC

North Georgia Technical College is a residential, public, multi-campus institution of higher education serving the workforce development needs of Northeast Georgia and part of the Technical College System of Georgia.

In his new role, Brown will work closely with the College of Lifetime Learning and Tech AI to develop innovative AI programs. He will identify industry needs and create interdisciplinary academic offerings serving a diverse range of learners, from K-12 students to executives. His initial emphasis will be on mid-career professionals seeking to upskill or reskill, equipping them with the technical skills essential for success in the AI field. He will also enhance existing programs and provide educational opportunities to companies and organizations, addressing current market demands.

Brown has more than 35 years of experience in professional education and supply chain optimization, including roles at IBM, Accenture, Chainalytics, Frito-Lay, and Tropicana. He has worked with executives in various industries, advising on supply chain management and securing $81 million in funding for AI in manufacturing through the Georgia AIM coalition.

In a statement, Brown said, “I look forward to contributing to innovative AI programs at Georgia Tech. Our goal is to create educational opportunities that meet the diverse needs of learners and equip them with the skills necessary to thrive in this evolving field.”

Brown’s leadership underscores Georgia Tech’s commitment to innovation and education in the rapidly changing landscape of AI. He is dedicated to establishing Georgia as a leader in AI and highlighting the resources and capabilities that Georgia Tech offers.

The magazine, available as open access at https://onlinelibrary.wiley.com/toc/23719621/2024/45/1, a one-year effort, spearheaded and co-edited by Ashok Goel, director of the National AI-ALOE Institute and professor of computer science and human-centered computing at Georgia Tech, along with Chaohua Ou, AI-ALOE’s managing director and assistant director, Special Projects and Educational Initiatives Center for Teaching and Learning (CTL) at Georgia Tech, and Jim Donlon, the NSF's AI Institutes program director.

In this issue, insights into the future of AI and its societal impact are presented by the three NSF AI Institutes headquartered at Georgia Tech:

• AI-ALOE: National AI Institute for Adult Learning and Online Education
  • Introduction to the Special Issue by Ashok Goel and Chaohua Ou.
  • The magazine features AI-ALOE’s work in reskilling, upskilling, and workforce development, showcasing how AI is reshaping adult learning and online education to prepare our workforce for the future.
• AI4OPT: AI Institute for Advances in Optimization
  • An overview of AI4OPT’s efforts in combining AI and optimization to tackle societal challenges in various sectors. The institute aims to create AI-assisted optimization systems for efficiency improvements, uncertainty quantification, and sustainability challenges, while also offering educational pathways in AI for engineering.
• AI-CARING: National AI Institute for Collaborative Assistance and Responsive Interaction for Networked Groups
  • AI-CARING’s section in the magazine details its comprehensive approach to using AI technologies to address the complex needs of aging adults, while navigating ethical considerations and promoting education in the field.
  • Co-authors contributing to AI-CARING's section include Sonia Chernova, associate professor at Georgia Tech and director of AI-CARING, along with members Elizabeth Mynatt, Agata Rozga, Reid Simmons, and Holly Yanco, all involved in AI-CARING research and education.

The magazine provides a comprehensive overview of how each of the 25 institutes is shaping the future of AI research.

About 'AI Magazine'

AI Magazine is an artificial intelligence magazine by the Association for the Advancement of Artificial Intelligence (AAAI). It is published four times each year, and is sent to all AAAI members and subscribed to by most research libraries. Back issues are available online (issues less than 18 months old are only available to AAAI members).

The purpose of AI Magazine is to disseminate timely and informative articles that represent the current state of the art in AI and to keep its readers posted on AAAI-related matters. The articles are selected to appeal to readers engaged in research and applications across the broad spectrum of AI. Although some level of technical understanding is assumed by the authors, articles should be clear enough to inform readers who work outside the particular subject area. 

To learn more, click here.

Bridging Academia and Industry

Van Hentenryck’s agenda included two sessions tailored to different audiences. The first, held in collaboration with Ciudad del Saber Foundation and the Panamanian Chamber of Technology, brought together entrepreneurs, tech sector leaders, and innovation advocates to discuss global trends in artificial intelligence. He highlighted the critical role AI will play in shaping future industries, underscoring how Georgia Tech can be a vital partner in accelerating Panama’s adoption of emerging technologies.

The second session, hosted at the Georgia Tech Panama Center, was an invitation-only gathering for professors and researchers specializing in AI and engineering disciplines. Van Hentenryck shared research insights, real-world applications of AI across various fields, and ideas for strengthening academic-industry collaboration.

Cultivating Strategic Relationships

While the visit was not part of a formal initiative, it marked a significant step toward deeper engagement. Van Hentenryck forged connections with technology entrepreneurs, university faculty, and representatives from the Secretaría Nacional de Ciencia, Tecnología e Innovación, Panama’s national science and innovation authority. These conversations opened the door to potential future partnerships and collaborative projects.

“This visit gave us the opportunity to connect Panama’s academic and private sectors,” said Van Hentenryck. “We see great potential for long-term collaboration that supports the country’s innovation goals.”

Looking Ahead

The Georgia Tech Panama Center anticipates that this exchange will lead to joint research, capacity-building, and the co-development of initiatives to strengthen AI and emerging technologies in Panama. The visit reflects Georgia Tech’s ongoing commitment to supporting global innovation through knowledge sharing and strategic partnerships.

Charmaine Dean, Vice-President of Research & International, shared, “The University of Waterloo is pleased to embark on a new collaboration with Georgia Tech, featuring faculty and student exchanges, joint research projects, dual degrees, and conferences. Strengthening ties between our institutions through this collaboration creates a dynamic environment for our faculty and students to foster innovation in many areas of mutual excellence.”

“Georgia Tech is excited to see its NSF AI Institute for Advances in Optimization (AI4OPT), under the leadership of Prof. Pascal Van Hentenryck, partner with experts from the Waterloo Artificial Intelligence Institute of the University of Waterloo. I am really looking forward to the impact that this partnership will have in advancing the fundamental knowledge of AI, in further expanding its applications, and in enabling its wider adoption,” noted Prof. Bernard Kippelen, Vice Provost for International Initiatives at Georgia Tech.

This collaboration is poised to elevate the academic and research landscape of both institutions, promoting global engagement and creating opportunities for students and faculty to thrive in an interconnected world.

Yongsheng Chen, Bonnie W. and Charles W. Moorman IV Professor in Georgia Tech's School of Civil and Environmental Engineering, has been awarded a $300,000 National Science Foundation (NSF) grant to spearhead efforts to enhance sustainable agriculture practices using innovative AI solutions. 

Georgia Tech has been actively engaged in artificial intelligence (AI) research and education for decades. Formed in 2023, the AI Hub is a thriving network, bringing together over 1000 faculty and students who work on fundamental and applied AI-related research across the entire Institute.  

“Pascal Van Hentenryck will drive innovation and excellence at the helm of Georgia Tech’s AI Hub,” said Abdallah. “His leadership of one of our three AI institutes has already shown his dedication to fostering impactful partnerships and cultivating a dynamic ecosystem for AI progress at Georgia Tech and beyond.” 

The AI Hub aims to advance AI through discovery, interdisciplinary research, responsible deployment, and education to build the next generation of the AI workforce, as well as a sustainable future. Thanks to Tech’s applied, solutions-focused approach, the AI Hub is well-positioned to provide decision makers and stakeholders with access to world-class resources for commercializing and deploying AI. 

“A fundamental question people are asking about AI now is, ‘Can we trust it?’” said Van Hentenryck. “As such, the AI Hub’s focus will be on developing trustworthy AI for social impact — in science, engineering, and education.” 

U.S. News & World Report has ranked Georgia Tech among the five best universities with artificial intelligence programs. Van Hentenryck intends for the AI Hub to leverage the Institute’s strategic advantage in AI engineering to create powerful collaborations. These could include partnerships with the Georgia Tech Research Institute, for maximizing societal impact, and Tech’s 10 interdisciplinary research centers as well as its three NSF-funded AI institutes, for augmenting academic and policy impact.  

“The AI Hub will empower all AI-related activities, from foundational research to applied AI projects, joint AI labs, AI incubators, and AI workforce development; it will also help shape AI policies and improve understanding of the social implications of AI technologies,” Van Hentenryck explained. “A key aspect will be to scale many of AI4OPT’s initiatives to Georgia Tech’s AI ecosystem more generally — in particular, its industrial partner and workforce development programs, in order to magnify societal impact and democratize access to AI and the AI workforce.” 

Van Hentenryck is also thinking about AI’s technological implications. “AI is a unifying technology — it brings together computing, engineering, and the social sciences. Keeping humans at the center of AI applications and ensuring that AI systems are trustworthy and ethical by design is critical,” he added. 

In its first year, the AI Hub will focus on building an agile and nimble organization to accomplish the following goals: 

• facilitate, promote, and nurture use-inspired research and innovative industrial partnerships;  

• translate AI research into impact through AI engineering and entrepreneurship programs; and 

• develop sustainable AI workforce development programs.  

Additionally, the AI Hub will support new events, including AI-Tech Fest, a fall kickoff for the center. This event will bring together Georgia Tech faculty, as well as external and potential partners, to discuss recent AI developments and the opportunities and challenges this rapidly proliferating technology presents, and to build a nexus of collaboration and innovation.  

“AI4OPT, with its focus on AI and optimization, will create new pathways for novel tools that allow better engineering applications to benefit society,” said Raheem Beyah, dean of Georgia Tech’s College of Engineering and Southern Company Chair. “This will allow engineers to build higher-quality materials, more efficient renewable resources, new computing systems and more, while also reinforcing the field as a career path for diverse students. The new institute complements the College’s commitment to the integration of AI in engineering disciplines.”

The interinstitutional team includes researchers and faculty from Georgia Tech, as well as the University of California, Berkeley; the University of Southern California (USC); Clark Atlanta University; the University of Texas at Arlington; and Spelman College.

“Optimization is now ubiquitous in society. Without it, the world would come to a halt,” said Van Hentenryck. “It is also at the core of the machine learning revolution. But as the world becomes increasingly interconnected, and also more uncertain, optimization problems have become daunting and incredibly challenging. Our institute will fuse AI and optimization to push the frontiers in decision making at massive scales.

“The vision is to merge AI and optimization to create intelligent agents that predict and quantify uncertainty, reason and optimize, continuously learn, and coordinate and collaborate. So, in a sense, the institute will transform optimization solutions into networks of intelligent systems.”

The team is driven by use cases in several areas of significant societal impact: energy systems and the use of massive, distributed renewable resources and demand response programs; green supply chains to support the growth of e-commerce; resilience and sustainability, particularly in how to develop local food production; and circuit design and control for accelerating the development of new computing systems that can solve these evermore challenging problems.

According to Van Hentenryck, a second significant component of the institute is to “democratize access to AI education, research, and jobs” for underrepresented minority and female students and teachers. Van Hentenryck brings experience to this task through his design and delivery of the Seth Bonder Camp in Computational and Data Science for Engineering, an online course and on-campus summer camp designed to increase awareness of the fields of data science and operations research among high school students. AI4OPT will build on this initiative by offering longitudinal camps to engage middle and high school students in these topics for the entirety of their secondary school education. The institute will also bring new AI education and research programs to HBCUs and Hispanic-serving colleges throughout the U.S., addressing the widening gap in job opportunities.

Van Hentenryck’s co-PIs are George Lan, ISyE A. Russell Chandler III Associate Professor; Justin Romberg, School of Electrical and Computer Engineering Schlumberger Professor; Professors Alper Atamturk and Dorit Hochbaum at UC Berkeley; Associate Professor Bistra Dilkina at USC; and Professor Charles Pierre at Clark Atlanta University. A significant number of faculty from computer science, civil and environmental engineering, electrical and computer engineering, and industrial and systems engineering across the various institutions are also involved, fostering the interdisciplinary nature of the institute.

For the first time, this year’s program includes major corporations, and the NSF Artificial Intelligence (AI) Institute for Advances in Optimization is partially funded by Intel Corporation. Van Hentenryck noted that industry collaborations represent a key constituency for AI4OPT: They drive the methodology research with use cases that represent fundamental societal challenges. 

In partnership with the United States Department of Agriculture, the National Institute of Food and Agriculture, the U.S. Department of Homeland Security Science & Technology Directorate, and the U.S. Department of Transportation Federal Highway Administration, the NSF is funding 11 centers within its National AI Research Institutions program. Georgia Tech has been awarded two of the grants: AI4OPT and AI Institute for Collaborative Assistance and Responsiveness Interaction for Networked Groups (AI-CARING), led by College of Computing Associate Professor Sonia Chernova to support aging-related issues.

“I am delighted to announce the establishment of new NSF National AI Research Institutes as we look to expand into all 50 states,” said NSF Director Sethuraman Panchanathan. “These institutes are hubs for academia, industry, and government to accelerate discovery and innovation in AI. Inspiring talent and ideas everywhere in this important area will lead to new capabilities that improve our lives from medicine to entertainment to transportation and cybersecurity and position us in the vanguard of competitiveness and prosperity.”

To learn more about the NSF Artificial Intelligence (AI) Institute for Advances in Optimization, visit https://www.ai4opt.org/.