College of Engineering and Computing

NSF CAREER award allows researcher to look under AI’s hood

Nathan Kahl — Mon, 20 Jul 2026 16:30:48 +0000

NSF CAREER award allows researcher to look under AI’s hood Nathan Kahl Mon, 07/20/2026 - 12:30

In This Story

Artificial intelligence (AI) systems are now part of everyday life, writing software, tidying up your shopping list, and answering questions. While we know they sit on top of large language models (LLMs), we still understand surprisingly little about what happens inside these systems or what is helping them generate responses.

Ziyu Yao. Photo provided

91�� Department of Computer Science Assistant Professor Ziyu Yao received a prestigious National Science Foundation (NSF) CAREER award for $674,100 over five years to peel the layers back on AI. Specifically, Yao will develop new methods for understanding the internal mechanisms of LLMs. Her research aims to make these AI systems more transparent and useful.

"We use language model–powered products every day, but we have very limited understanding of how they actually work," Yao said. Most efforts to evaluate AI systems focus on their behavior. Researchers give a model a prompt and judge the quality of its response. Yao's work instead focuses on mechanistic interpretability, an emerging field that examines what happens inside a language model as it processes information.

"If we send something to the model, we want to see how it extracts features or signals from my input and gradually performs computations before producing an answer," she said.

As language models have grown dramatically in size, that task is increasingly difficult. Today's leading models contain potentially hundreds of billions of parameters. And Yao said, "The interpretability research community has not caught up. Many traditional approaches cannot be efficiently applied to today's language models."

The project focuses specifically on AI-powered code generation, in which users describe a programming task in natural language and an AI system generates software code. Code generation is an increasingly important application of LLMs, with uses including software engineering and scientific research.

Yao's team will investigate how LLMs apply programming syntax, recall semantic knowledge, and perform deliberate reasoning while writing code. The researchers will also study how training data and learning methods influence those internal mechanisms and explore how interpretability insights can be used to improve AI coding systems.

Current interpretability studies often require researchers to manually design experiments, collecting internal model signals and analyzing the results. Yao plans to develop a framework that automates much of that process using AI itself, allowing researchers to study LLMs more efficiently.

At the same time, she wants interpretability research to produce practical benefits rather than simply satisfying scientific curiosity.

"We want to build the bridge between what we discover about language models and how that knowledge can improve them," Yao said. "Can interpretability actually help us build better AI systems?"

Although commercial AI systems such as ChatGPT are proprietary, Yao and colleagues primarily study open-weight language models that are downloadable. These models are becoming increasingly competitive with commercial systems while supporting the transparency needed for scientific research.

An expectation with the award and a hallmark of the CAREER program is a plan for broader impact. Yao hopes to expand AI literacy through outreach programs, create new curricula and open-source educational resources, provide undergraduate research opportunities, and foster collaborations between researchers in artificial intelligence and software engineering.

"I think we should encourage the younger generation to embrace AI," Yao said. "But at the same time, they should be skeptical, think critically, and be careful about what they are reading from AI."

Topics

large language models

National Science Foundation

Artificial Intelligence

College of Engineering and Computing

Research

George Mason researcher develops an affordable helping hand for stroke recovery

Nathan Kahl — Tue, 14 Jul 2026 19:25:34 +0000

George Mason researcher develops an affordable helping hand for stroke recovery Nathan Kahl Tue, 07/14/2026 - 15:25

For millions of stroke survivors, something as simple as picking up a glass of water or holding a sandwich is a daily challenge. Quentin Sanders wants to make those moments easier through wearable robotic technology designed to restore hand function.

The 91�� assistant professor is developing a new generation of hand exoskeletons that may help people regain independence after stroke. His lab is testing wearable devices that amplify a user's remaining muscle activity, allowing them to open and close their hand more effectively while remaining affordable enough for broader use.

Sanders' prior work focused on lower-limb prosthetics. Photo by Ron Aria/Office of University Branding

The latest prototype resembles a lightweight glove that fits over the hand and upper arm. As users attempt to move their hand, the device detects their remaining muscle activity and assists the motion.

"We instruct them to try to open their hand," Sanders explained. "When they try to open their hand, we sense whatever residual activity they have, and then the exoskeleton amplifies that."

One version of the device seeks to use wearable ultrasound technology developed in collaboration with George Mason researcher Siddhartha Sikdar, a professor in the Department of Bioengineering and director of the Center for Medtech Innovation. The system will use wearable ultrasound sensors to monitor how muscles deform as they contract, translating those signals into movement. Another simpler version uses a button embedded in the glove that users press to control the device.

While brain-controlled devices remain the long-term aspiration for many in the field, Sanders is focused on a more practical solution that builds on the muscle activity people retain after a stroke. "I would say brain-controlled systems is kind of the holy grail. In my lab, we're going one level lower to see if we can use muscle activity to control it."

The need for better rehabilitation tools is growing. Sanders noted that roughly 800,000 people experience a stroke each year in the United States, while millions more live with its long-term effects. Advances in medicine mean more people survive strokes, but many struggle to access the lengthy rehabilitation needed to regain function.

"We're at this point where you're living a long life, but you have this need for rehab," Sanders said. "You need either consistent opportunities for movement or some type of device that can help improve your quality of life."

Commercial hand exoskeletons remain scarce in the United States, and many existing systems cost tens of thousands of dollars. Making the technology more affordable and accessible has become one of the driving goals of his research.

"You've got this large population of people who need these devices who aren't getting them," Sanders said. "I'm hoping we can make this kind of low-cost, accessible version that people can use to improve some aspect of their life."

Sanders is also working to broaden who can benefit from rehabilitation technologies. Many research studies enroll only patients who meet narrow eligibility criteria, leaving others without solutions tailored to their needs.

"I think that's the other breakthrough people are working on that my lab is working on," he said. "How can we make these devices work for a larger population?"

Learn more about George Mason's Grand Challenge Initiative

Explore Research at George Mason

In This Story

Quentin Sanders

Siddhartha Sikdar

Topics

Prosthetic Arm

Bioengineering

mechanical engineering

Research

College of Engineering and Computing

GCI-Health

91�� and Phase Inc. receive NSF grant to advance 3D-printed microfluidic technology

Martha Bushong — Wed, 01 Jul 2026 18:37:20 +0000

91�� and Phase Inc. receive NSF grant to advance 3D-printed microfluidic technology Martha Bushong Wed, 07/01/2026 - 14:37

91�� and Phase Inc. have received a National Science Foundation (NSF) STTR grant to advance a new generation of 3D-printed microfluidic devices that could help move the technologies from the research lab toward broader commercial and scientific use.

Ramin M. Hakami and Remi Veneziano. Photo provided

The project combines the expertise of College of Science Professor Ramin M. Hakami’s group in extracellular vesicle (EV) biology, and that of College of Engineering and Computing Associate Professor Remi Veneziano’s group in bioengineering and materials characterization, at 91�� with Phase’s vision to create an end-to-end, automated microfluidic platform that brings together custom device design, scalable 3D-printed polydimethylsiloxane (PDMS) chip manufacturing, and automated fluid handling. Specifically, this project leverages the microfluidic EV platform jointly developed and published by the Veneziano and Hakami groups.

Microfluidic devices use tiny channels to control small amounts of fluid and recreate environments on a cellular scale. They model human biology more realistically than flat cell cultures, making them important for drug discovery, disease research, and toxicology. Microfluidics are especially timely as the FDA has announced plans to phase out some animal testing requirements and encourage more human-relevant methods.

Today, producing complex PDMS microfluidic devices often requires cleanrooms, manual optimization, and repeated trial-and-error. The NSF-supported work is designed to reduce that bottleneck by using thermal and curing models to predict how PDMS will behave during printing, then optimize print parameters before a device is manufactured.

Photo provided

“This partnership helps us move one step closer to a fully automated, scalable microfluidic platform,” said Jeff Schultz, principal investigator and co-founder of Phase, which is headquartered in Charlotte, North Carolina. “Our goal is to make microfluidic technology more reproducible and more accessible to researchers and companies working to develop better human-relevant models.”

George Mason researchers will help characterize the printed devices for dimensional accuracy, surface quality, batch-to-batch consistency, and biological function. The team will also test a device designed to study EV function. EVs are nanoparticles that are released by cells and play critical roles in intercellular communication. They have been shown to carry important regulatory functions in various human diseases, such as cancer, infectious disease, and neurological disorders, and are also highly advantageous for use in drug delivery.

“Being able to rapidly and cost‑effectively prototype and fabricate custom microfluidic devices will significantly enhance our capacity to design relevant microphysiological systems and will help broaden access to this technology to many research laboratories” said Veneziano.

“Our microfluidic device empowers researchers to conduct functional EV studies with ease and under physiologically relevant conditions. Through our partnership with Phase to 3D print the chips, we will be able to deliver more reliable, cost-effective, and commercially viable tools to the EV scientific community,” said Hakami, co-director of the Center for Infectious Disease Research at George Mason.

For Phase, the NSF grant builds on a growing base of support from federal and private sources. The company has already received more than $3.5 million in nondilutive funding, including support from the National Institutes of Health, the One North Carolina Small Business Program, the North Carolina Biotechnology Center, NSF, and private-sector partners. Previous research partners include Harvard Medical School, Georgia Tech, and Virginia Tech.

By pairing George Mason’s biological and engineering strengths with Phase’s manufacturing platform, the project is positioned to advance both scientific discovery and commercialization. The result could be a more reliable path for producing the microfluidic tools needed to support the next wave of biomedical research, organ-on-a-chip development, and human-centered bio-innovation.

This research supports the Grand Challenge Initiative's goal of improving human health, well-being, and preparedness

Discover more GCI health and well-being research >>

Learn about other solutions >>

Explore Research at George Mason

In This Story

Remi Veneziano

Topics

College of Engineering and Computing

GCI-Health

Patriot Profile: Mia Arevalo-Delcid

Katarina Benson — Tue, 30 Jun 2026 18:06:50 +0000

Patriot Profile: Mia Arevalo-Delcid Katarina Benson Tue, 06/30/2026 - 14:06

When the call-up to El Salvador's Senior National Team finally came through, Mia Arevalo-Delcid didn't need a moment to let it sink in. She already knew exactly what it meant. "That's the big leagues right there," said the George Mason women's soccer standout. "It's all eyes in the country on you. It's going to be amazing.”

Mia Arevalo-Delcid. Photo by Rafael Suanes/George Mason Athletics.

Home and Away: Arevalo-Delcid, a Manassas, Virginia, native and dual citizen of the United States and El Salvador, has been representing El Salvador on the pitch since earning her first call-up to the Salvadorian U20 National Team in 2022. That experience gave her a taste of something she hadn’t expected: the electricity of playing in front of family. "Family means everything to me," she said. "Everyone was so excited for me. We were in the newspaper, and my family bought like 50 papers. Representing my country was one of the best moments of my life."

Ready for the Big League: This summer, she did it again—only on a much bigger stage. She traveled south in early June to train with El Salvador’s top players for several weeks before a series of friendly competitions against neighboring countries. "I love playing for my family's home country," she said. "It's a way to honor my heritage."

“It's really pretty amazing,” said Aaron Brunner, George Mason women’s soccer head coach. "It's such a tremendous honor to represent your country. But I'm not surprised because Mia is so amazing."

Homegrown: The road to San Salvador ran through some familiar Northern Virginia zip codes first. Arevalo-Delcid was a four-year letterwinner and team captain at Colgan Senior High School in Manassas, earning All-District First Team, All-Region, and Honorable Mention for the Washington Post’s All-Met honors. She also starred in club soccer with the Virginia Development Academy (VDA), one of the top programs in the region, earning ECNL Mid-Atlantic Conference First Team honors in her junior year and a ranking of No. 16 prospect in the Mid-Atlantic region by Top Drawer Soccer. She went on to James Madison University before transferring to George Mason in spring 2025. The decision was personal. "I wanted to be closer to home," Arevalo Delcid said, "and I believed in what Coach Brunner was building here."

A Team Player: Arevalo-Delcid quickly established herself as not only one of the team’s best players, but as one of its leaders. A natural attacking midfielder, she willingly shifted to a more defensive role to fill a need for the Patriots—and still managed to contribute a goal and two assists in her first season. “She had a great year for us and was always willing to do whatever the team needed of her,” said Brunner. “She’s grown a lot, she's learned a lot, and her confidence is high.”

This spring, Arevalo-Delcid signed with Loudoun United's semi-pro league. Photo by George Mason Athletics.

Turning Pro: The national team call-up is just one line on a resume that's been filling up fast. This spring, Arevalo-Delcid signed with Loudoun United in the USL W semi-pro league and landed an NIL deal with Tinycup Coffee, a George Mason alumni-owned company.

"A dynamic and tireless presence in the midfield," Loudoun United Head Coach Christian Cziommer said at signing. "Known for her relentless work rate and creative flair, she brings significant high-level experience to our roster."

Beyond the Pitch: When she's not training or playing, Arevalo-Delcid—a civil engineering major in the College of Engineering and Computing—works as a substitute teacher at Woodbridge High School, tutoring Latino students and helping them prepare for AP exams, and holds down a part-time job at a Starbucks near campus. "Yes, it's a lot," she said. "But you have to work for anything worth having."

Eyes on the Future: Arevalo-Delcid turned 21 in June, right around the time she boarded a plane for El Salvador. She's already thinking about what comes next and a professional soccer career is squarely in her sights. "I want to try," she said. "I want to see whatever opportunity I can get. Going to El Salvador has definitely been a game changer for me."

Brunner likes her chances. "She's going to be ready," he said, "and I think she's going to do awesome."

Topics

Patriot Profile

Student Athlete

Athletics

College of Engineering and Computing

NIL

Students

Stephanie Shanahan is July Employee of the Month

Katarina Benson — Mon, 29 Jun 2026 16:02:22 +0000

Stephanie Shanahan is July Employee of the Month Katarina Benson Mon, 06/29/2026 - 12:02

Stephanie Shanahan, a human resources assistant in the College of Engineering and Computing (CEC) at 91��, is known for being able to do it all. In their letters of support, her colleagues emphasized her attention to detail, reliability, and willingness to help. In recognition of her dedication, expertise, and unwavering support of the CEC community, she has been named July Employee of the Month.

President Washington with July Employee of the Month Stephanie Shanahan. Photo by Evan Cantwell/Office of University Branding

“Stephanie is an outstanding employee in every way,” said Karen Witt, CEC director of human resources. “Her real gift is her attention to detail. She regularly spots errors and quickly and expertly fixes the problems.”

Kim Goodwin-Slater, chief business officer, said, “Not only is Stephanie knowledgeable and her work of high value, she is also one of the most collaborative and supportive team members in the college.”

Shanahan’s support of her coworkers was mentioned by several colleagues. “Stephanie is consistently friendly, approachable, and generous with both her time and her expertise,” said Lizzie Barnfield, academic affairs and administrative coordinator in CEC’s Office of the Dean.

“Her willingness to help is sincere and constant,” said Elizabeth Dean, manager of administration and strategic projects. “She never hesitates to lend a hand, answer questions, or take on additional work when needed.”

“Stephanie's administrative support was vital to hiring the new IT director of the College of Engineering and Computing. She made the hiring process efficient and was fun to work with,” said Kevin Hicks, director of operations and facilities projects at CEC.

How did you come to Mason:

After several years of volunteering with the Navy–Marine Corps Relief Society as chair of volunteers, I was ready to reenter the workforce. I applied to the George Mason Temp Pool and was later asked to stay on as a wage employee in the same role. It was a wonderful opportunity and a great fit for me.

Best day on the job:

I don’t have just one best day, but I would consider a “best day” on the job to be one when I feel that I’ve been most helpful to my coworkers.

What do you like best about working at Mason:

Definitely the people. Everyone I interact with here truly enjoys working at George Mason, so it’s lovely to work in environment where people genuinely want to be.

What do you like to do when you’re not working:

My favorite things to do when I’m not working are walking—with or without my dog, traveling to new places, and reading books. We have a great monthly book club in the College of Engineering and Computing, so I always receive great recommendations from my colleagues.

Topics

Human Resources

College of Engineering and Computing

Employee of the Month

Faculty and Staff News

George Mason launches new MS in quantum science and engineering

ckearney — Mon, 15 Jun 2026 18:23:34 +0000

George Mason launches new MS in quantum science and engineering ckearney Mon, 06/15/2026 - 14:23

91�� has launched a new master of science in quantum science and engineering, the first program of its kind in Virginia and one of only a handful in the United States. Designed to meet growing workforce demand in one of the world's fastest-evolving technology sectors, the program prepares students to apply quantum technologies across disciplines including mathematics, physics, computing, engineering, cybersecurity, chemistry, and biology.

Designed to meet growing workforce demand in one of the world's fastest-evolving technology sectors, the MS program prepares students to apply quantum technologies across disciplines. Photo provided

Quantum technology is transforming industries ranging from computing and cybersecurity to healthcare and energy. As investment in quantum research and development continues to grow worldwide, so does the need for professionals who can bridge traditional STEM fields with emerging quantum technologies.

The degree was developed in direct response to industry demand for a workforce that can bridge traditional disciplines and emerging quantum technologies.

“When we talked to industry, they told us they want experts in STEM fields who also have knowledge of quantum science and engineering,” said Jessica Rosenberg, professor in the Department of Physics and Astronomy and director of education for the Quantum Science and Engineering Center.

Reflecting the inherently interdisciplinary nature of the field, students enter the program with backgrounds in STEM disciplines, such as mathematics, physics, computer science, or engineering, and build quantum expertise alongside domain-specific knowledge. The curriculum integrates foundational training in quantum information science and engineering while allowing students to deepen their applied-area expertise through electives in external disciplines.

The master's program focuses on three key areas: quantum computing and algorithms, quantum communications and security, and quantum sensing and measurement technologies.

Rather than training students solely as quantum specialists, the program emphasizes preparing them to apply quantum tools within their primary fields.

Photo provided

“Our goal is not to train pure quantum scientists,” said Michael Jarret, assistant professor in the Department of Mathematical Sciences and Department of Computer Science. “We're training professionals who can operate between domains—people who can connect quantum concepts to real-world applications.”

A defining feature of the program is its emphasis on experiential learning. Students complete a master's research project, often in collaboration with industry partners or research laboratories, gaining real-world experience in quantum applications and emerging technologies.

This flexible structure allows the program to evolve alongside the field itself. “As the quantum industry grows over the next decade, this degree is designed to adapt with it,” Jarret added.

Through this approach, graduates will be well-positioned to evaluate and implement quantum solutions in both academic and applied settings while also communicating complex concepts to diverse audiences. The program is designed to be accessible to a wide range of learners, from current undergraduates to working professionals.

George Mason also offers a Bachelor’s-to-Accelerated Master’s (BAM) pathway, enabling qualified undergraduates at George Mason to begin working toward the degree during their junior or senior years. At the same time, the program welcomes students entering directly into the master’s, creating opportunities for both early-career and returning learners to engage with quantum technologies.

As quantum technologies continue to reshape fields from computing and cybersecurity to healthcare and energy, programs like George Mason’s MS in quantum science and engineering are critical to building the next generation of talent.

This program is jointly offered by the College of Science and the College of Engineering and Computing.

Learn about the program

Topics

Campus News

College of Science

College of Engineering and Computing

quantum

GCI-Digital

George Mason engineering team uses robotics to rethink accessibility

Katarina Benson — Tue, 09 Jun 2026 13:58:00 +0000

George Mason engineering team uses robotics to rethink accessibility Katarina Benson Tue, 06/09/2026 - 09:58

Many accessibility surveys depend on manual measurements, handwritten notes, and extensive walkthroughs with compliance checklists. A team of 91�� engineering students wondered if a robot could do it faster. Nine months later, they created one.

The project, called Salus, combines robotics, LiDAR technology, object detection, GPS mapping, cloud-based analytics, and a custom-built website to help survey public spaces for potential ADA accessibility barriers. Developed as part of a College of Engineering and Computing senior capstone project by mechanical engineering majors Lexi Chivers, Connie Lam, Mariah Tammera, Noemi Umanzor, and Tyler Yared, the system is designed to automate portions of the accessibility surveying process while allowing engineers and designers to better understand how people with disabilities experience physical spaces.

The Salus team with the robotic accessibility surveying system they developed as part of their senior capstone project at 91��. Photo provided

Salus was one of several George Mason capstone projects supported through a GO Virginia-funded initiative led by the Nexus234 Innovation District, which pairs students with industry-informed challenges and mentors.

“We saw a system that was operating poorly, and we wanted to optimize it,” said Chivers, the team lead.

The idea originated when one of Chivers’ teammates attended a conference and discussed the difficulties of collecting large volumes of survey data in the field with industry professionals.

“They basically said, ‘We wish we had something we could send out to collect data and not have to constantly manage,’” said Chivers. “That conversation sparked everything.”

The project consumed most of the team’s weekends as they worked through testing, software integration, fabrication, and constant iteration.

“A lot of people told us we weren’t going to be able to do this in nine months,” said Chivers. “At one point, someone told us it would take two years and eight NASA engineers.”

Instead, the students delivered a working proof of concept before graduation.

As the robot moves through a space, it uses LiDAR sensors, GPS mapping, and onboard cameras to identify and document potential accessibility issues. The data is processed through cloud-based systems and displayed through an interactive website. Rather than sorting through raw data, users can explore flagged locations through an interactive visual map built by the team.

For Chivers, the project also had a personal connection. She said her mother’s job teaching students with disabilities influenced the team’s conversations around accessibility and inclusion. “Just because something legally meets ADA standards doesn’t always mean it’s truly accessible for those with disabilities,” she said.

Kenan Aden, COO of Didlake and the team’s industry mentor, was introduced to the student team through Nexus234. He said the project impressed him both from its technical complexity and for the problem it set out to tackle.

“The entire team approached this project with an incredible level of determination and systems thinking,” said Aden. “What makes it especially meaningful is that they never lost sight of the people this technology is intended to help.”

"This team’s focus and dedication have been extremely impressive," said Leigh McCue, professor and chair of George Mason’s Department of Mechanical Engineering. "Any time I popped my head into the senior design space, or walked visitors through for a tour, the team was hard at work and eager to showcase their technology."

One of the most rewarding parts of the experience for Chivers was discovering the kind of engineer she wants to become.

“I thought I wanted to stay in the background,” said Chivers. “But this project made me realize I really love being a leader, solving problems, and doing things that actually matter to people.”

Currently, the students are working with George Mason’s Office of Technology Transfer to explore patent protection for the project’s intellectual property. Although the team is still deciding what comes next, Chivers said the technology has potential beyond the capstone project itself, including with construction firms, municipalities, designers, and accessibility planners.

In her advice to other entrepreneurs, Chivers said, “Your dreams are never too big. You just haven’t found all the tools you need to make them happen yet.”

Learn about Research at George Mason

Topics

College of Engineering and Computing

Timing the perfect hardware hack

tdonnel — Tue, 09 Jun 2026 13:35:43 +0000

Timing the perfect hardware hack tdonnel Tue, 06/09/2026 - 09:35

Roombas have become a familiar part of everyday life, quietly navigating living rooms and kitchens. But behind that convenience is a complex system of sensors, algorithms, and data processing—and, as a group of 91�� cyber security engineering (CYSE) students—Finn Schaefer, Ryan Lam, Sidarth Kumar, Jimmy Tram, and Neil Sharma—discovered, a surprising vulnerability. Their capstone project research was accepted for presentation at one of the most prestigious venues for hardware-based security research, the IEEE International Symposium on Hardware Oriented Security and Trust (HOST).

“It just scans the room, goes around, and starts mapping," said Finn Schaefer, comparing the vacuum cleaner to the robot at the center of his team's project.

These autonomous systems rely on technologies like LiDAR and SLAM (simultaneous localization and mapping) to build a virtual map of their environment and navigate safely. However, that same reliance on sensor data also opens the door to cyberattacks that can alter a robot’s perception, sometimes with dramatic consequences.

From left to right: Finn Schaefer, Neil Sharma, Ryan Lam, Sidarth Kumar, and Jimmy Tram. Photo provided.

The capstone project, advised by Assistant Professor Tanvir Arafin, challenged students to explore exactly that risk. From the outset, Arafin encouraged an open-ended, research-driven approach.

“Professor Arafin basically told us to try to break ROS, a robot operating system,” Schaefer said.

The assignment functioned as a “red-team” exercise, pushing students to think like attackers to understand vulnerabilities in autonomous systems.

The team’s early ideas focused on overwhelming the robot with false data, effectively flooding it with noise. But this proved too obvious. That initial concept “was really simple and easy to detect,” said Ryan Lam. A more subtle approach would be needed to create a meaningful, realistic attack.

Their breakthrough came in the form of a timing-based method that mimicked the robot’s normal operating patterns. Instead of bombarding the system, they carefully injected altered sensor data at precisely the right intervals.

“We eventually got to our more elegant solution, where we’re able to match the timing pattern that the robot actually expects,” Schaefer said. Because the manipulated data looked plausible and arrived in the expected cadence, the robot accepted it as real.

A judge examines the team's robot at the CYSE senior design event. Photo by Teresa Donnellan/CEC

The effect was striking: the robot’s internal map gradually diverged from reality. Even small manipulations could cause significant errors.

“With 2- to 5-percent drift, it would crash into walls,” Schaefer said.

In some cases, the system could be tricked into perceiving obstacles that didn’t exist. “It would see a wall that’s not actually there,” he added.

The team also demonstrated the ability to shrink or expand the robot’s perceived environment, causing navigation failures.

To prove the effectiveness of their approach, the students combined simulated analysis with real-world testing. They compared baseline maps to manipulated ones over time and observed the robot attempting to navigate using corrupted data.

“These comparisons served as the proof that we used to say that this works,” said team member Sidarth Kumar.

Additional testing showed that the attack remained effective even under network congestion.

This capstone project reflects Arafin’s broader work to secure the next generation of mobility systems, from connected vehicles to robotics. Moreover, the students came away with a deeper understanding of the emerging field of hardware security.

Tanvir Arafin (center) with the 2026 senior capstone teams he advised. Photo provided.

“This is an exceptional accomplishment and a testament to the curriculum rigor of the Cyber Security Engineering Department, reinforcing a tradition of excellence in undergraduate research at CYSE,” said Arafin. “Over the last few years, CYSE undergraduate students from our group have earned recognition at multiple national and international venues in transportation and autonomous systems security, notably the best demo award in the 18th Association for Computing Machinery Conference on Security and Privacy in Wireless and Mobile Networks and the first, second, and third places at the National Transportation Cybersecurity Competition. All of these accomplishments highlights both the students’ dedication and the strength of undergraduate research within our CYSE Department.”

In an era where autonomous systems are becoming increasingly common, from household robots to self-driving cars, the team’s work underscores a critical lesson: If a machine’s understanding of the world can be manipulated, so can its behavior. What seems like a harmless household device may, under the hood, share the same vulnerabilities as far more complex systems. And as these students demonstrated, understanding those vulnerabilities is the first step toward securing the future of autonomous technology.

Discover more Research at George Mason

Learn more about the College of Engineering and Computing

In This Story

Tanvir Arafin

Topics

Cybersecurity Research

Senior Capstone Project

Undergraduate Research

Research

College of Engineering and Computing

competitions

Students

Why did the AI agent cross the road?

tdonnel — Mon, 08 Jun 2026 18:31:17 +0000

Why did the AI agent cross the road? tdonnel Mon, 06/08/2026 - 14:31

Workshopping, an iterative process where creators share ideas, test what works, and refine what doesn’t through collective feedback, is at the heart of any writers’ group. This collaborative dynamic inspired 91�� PhD students Shiwei Hong to explore whether artificial intelligence (AI) could benefit from a similar approach.

Hong developed a novel multi-agent system that simulates a collaborative comedy writing environment in which AI agents generate, critique, and refine humorous content together. Her research, recently accepted to the prestigious 64th Annual Meeting of the Association for Computational Linguistics, investigates how structured interaction among AI agents can improve creative output.

Shiwei Hong. Photo provided.

Humor remains challenging for artificial intelligence. “Generating a joke or something that is very funny is actually a very tricky question, because it requires a lot of how humans interpret the generated piece,” said Hong, who is working on a degree in computer science.

She created a “sandbox” environment to mirror real-world creative collaboration, populated by 35 AI agents assigned distinct roles and personalities powered by GPT-4.

“Five agents acted as performers. The rest acted as critics or audience members,” said Hong.

Designing 35 unique agent personas required imagination as well as technical expertise. Drawing on her interest in writing fiction, Hong created characters with varied social and cultural backgrounds, adding depth to the simulated interactions.

In one experimental environment, the performer agents generated two scripts in sequence without feedback; in another, they engaged the audience members in critique and discussion between the rounds of generation. The difference was significant.

Human evaluators compared outputs across multiple criteria, such as humor, coherence, and social tone. In more than 70 percent of cases, evaluators preferred scripts produced in the second round of the discussion-based environment.

The improvement appears to stem from collective learning. As agents interact, they build on shared insights, identifying patterns in audience preferences and refining their outputs accordingly. Technically, this process is supported by a shared conversational memory stored in a vector database, allowing agents to retrieve relevant past exchanges and incorporate them into new content. The result is an iterative, emergent form of creativity that begins to resemble human collaboration.

Looking ahead, Hong and her advisor, Assistant Professor Zhicong Lu, aim to expand the system by incorporating human participants and richer modes of interaction. Future directions include integrating voice, gestures, and immersive technologies such as virtual and augmented reality to better capture the nuances of live performance.

“In real comedy, we have faces, gestures, and real voices,” she said. “We hope to bring more of that into the system.”

By demonstrating that workshopping can significantly enhance machine-generated humor, Hong’s work suggests the future of artificial intelligence may lie not only in more advanced individual models, but also in communities of agents learning, creating, and perhaps even laughing together.

Overview of Multi-Agent Comedy Club. Credit: arXiv (2026). DOI: 10.48550/arxiv.2602.14770

Learn about Artificial Intelligence at George Mason

Explore Research at George Mason

Topics

Human Computer Interaction

computer science

College of Engineering and Computing

Artificial Intelligence

doctoral students

Research

George Mason engineering students turn personal experience into accessibility innovation

ckearney — Tue, 02 Jun 2026 20:58:30 +0000

George Mason engineering students turn personal experience into accessibility innovation ckearney Tue, 06/02/2026 - 16:58

For Owais Yousuf, inspiration began at home. His father, who contracted polio as a child, relied on crutches to move through daily life. Growing up, Yousuf watched him navigate airports and crowded spaces with difficulty. Three of his fellow 91�� mechanical engineering students had similar experiences with relatives who struggled with mobility. The four of them began wondering: How do you make airport travel more independent and less stressful for people with mobility challenges?

From left, Calvin Nguyen, Javier Carpio Jota, Turner Applegate, and Owais Yousuf, creators of the B-Drive, with their prototype. Photo provided

The answer to that question became B-Drive, a senior capstone project developed by Yousuf, Turner Applegate, Javier Carpio Jota, and Calvin Nguyen that combines autonomous navigation, computer vision, and adaptive mobility technology to help wheelchair users move through transportation hubs on their own terms.

B-Drive was one of several George Mason capstone projects supported through a GO Virginia-funded initiative, led by the Nexus234 Innovation District, which pairs students with industry mentors and opportunities to address pressing needs.

"The people we love aren't just statistics," said Yousuf, the team's lead. "They're people we care about. We've seen the frustrations they face firsthand. That experience gave us the context to build something that could provide them some relief."

As the team dug deeper, they found that navigating a large airport can present obstacles at nearly every step. Long walks, unfamiliar layouts, limited assistance, and confusing signs can make traveling on their own difficult for many passengers.

To better understand those barriers, the team participated in the National Science Foundation's I-Corps program, which helps entrepreneurs move a business idea or discovery toward licensing or commercialization. Program participants assess the commercial viability of their idea by conducting customer interviews and working closely with a mentor. Yousuf and his team spoke with travelers, transportation professionals, accessibility advocates, and industry experts.

"We consistently heard that people wanted the freedom to move through an airport with greater dignity and confidence," said Yousuf.

Those conversations led to B-Drive. The team decided early on that B-Drive needed to fit into existing airport operations, so they designed it to work with wheelchairs already found in many airports.

Bringing B-Drive to life required more than technical expertise. After delays in obtaining testing equipment, the team drove to New Jersey to buy a wheelchair themselves rather than wait.

Members of the B-Drive team demonstrate their prototype. Photo provided

Their persistence impressed Robert "Bob" Schneider, executive director of OmniRide and the team's industry mentor, who was introduced to the students through Nexus234.

"They didn't let anything stop them. They went out and got it done," said Schneider.

Schneider guided the students as they narrowed the project's scope and found a realistic way to put their ideas into action. He suggested the team pick one clear, manageable use case. They decided to focus on a journey that’s familiar to many travelers at Washington Dulles International Airport: getting from the Silver Line Metro station to their destination inside the airport.

As the project progressed, the students began thinking beyond the classroom. The team is currently exploring intellectual property protection and potential avenues for commercialization through George Mason's Office of Technology Transfer.

Leigh McCue, professor and chair of George Mason’s Department of Mechanical Engineering, believes that moving from classroom projects to real-world applications is among the most valuable lessons for students.

"One of the hardest parts of engineering is defining the right problem to solve," said McCue. "This team resisted the temptation to build technology for its own sake and grounded their approach in the experiences of the people they aimed to empower.”

The project also prompted Yousuf to rethink what it means to be an engineer. "Engineering is ultimately about people," said Yousuf. "Technology is only valuable if it improves someone's life. That's what motivated us from the beginning, and it's what continues to motivate us now."

Graduation marked the end of the capstone project, but the team hopes B-Drive's story is only beginning. The goal remains the same for Yousuf as when the project first started on a whiteboard.

"We're not going to stop until we bring a smile to people's faces," said Yousuf. "That's what this has always been about."

In This Story

Leigh McCue-Weil

More Mechanical Engineering from George Mason

Topics

College of Engineering and Computing

Science and Technology Campus

College of Engineering and Computing

NSF CAREER award allows researcher to look under AI’s hood

In This Story

Topics

George Mason researcher develops an affordable helping hand for stroke recovery

Related News

In This Story

Topics

91�� and Phase Inc. receive NSF grant to advance 3D-printed microfluidic technology

Related Stories

In This Story

Topics

Patriot Profile: Mia Arevalo-Delcid

Related News

Topics

Stephanie Shanahan is July Employee of the Month

How did you come to Mason:

Best day on the job:

What do you like best about working at Mason:

What do you like to do when you’re not working:

Topics

George Mason launches new MS in quantum science and engineering

Related News

Topics

George Mason engineering team uses robotics to rethink accessibility

Related Stories

Topics

Timing the perfect hardware hack

Related Stories

In This Story

Topics

Why did the AI agent cross the road?

Related Stories

Topics

George Mason engineering students turn personal experience into accessibility innovation

In This Story

Related News

Topics

College of Engineering and Computing

NSF CAREER award allows researcher to look under AI’s hood

In This Story

Topics

George Mason researcher develops an affordable helping hand for stroke recovery

Related News

In This Story

Topics

91���� and Phase Inc. receive NSF grant to advance 3D-printed microfluidic technology

Related Stories

In This Story

Topics

Patriot Profile: Mia Arevalo-Delcid

Related News

Topics

Stephanie Shanahan is July Employee of the Month

How did you come to Mason:

Best day on the job:

What do you like best about working at Mason:

What do you like to do when you’re not working:

Topics

George Mason launches new MS in quantum science and engineering

Related News

Topics

George Mason engineering team uses robotics to rethink accessibility

Related Stories

Topics

Timing the perfect hardware hack

Related Stories

In This Story

Topics

Why did the AI agent cross the road?

Related Stories

Topics

George Mason engineering students turn personal experience into accessibility innovation

In This Story

Related News

Topics

91�� and Phase Inc. receive NSF grant to advance 3D-printed microfluidic technology