News

The Amazon–Virginia Tech Initiative for Efficient and Robust Machine Learning will support two Amazon Fellows and five innovative research projects led by Virginia Tech faculty in the 2023-24 academic year that further the initiative’s mission of advancing innovation in machine learning. 

The initiative, launched in 2022, is funded by Amazon, housed in the College of Engineering, and directed by researchers at the Sanghani Center for Artificial Intelligence and Data Analytics on Virginia Tech’s Blacksburg campus and at the Virginia Tech Innovation Campus in Alexandria. 

An open call for fellowship nominations and faculty projects went out across the Virginia Tech campuses. An advisory committee of Virginia Tech faculty and Amazon researchers selected two Amazon Fellows from 27 nominations — more than double what was received last year — and five faculty projects from 17 submitted proposals. Read full story here.

Faculty are considering how AI models such as ChatGPT can customize learning by producing dynamic case studies or offering instant feedback or follow-up questions. Many are making AI the subject of assignments. They’re asking students to analyze and identify weaknesses in arguments produced by ChatGPT, for instance, or to edit an AI-produced essay with “track changes” on.

That kind of critical thinking about generative AI is vital, said Ismini Lourentzou, assistant professor of computer science in the College of Engineering and core faculty at the Sanghani Center for Artificial Intelligence and Data Analytics. “It’s our responsibility as educators to teach students how to use these tools responsibly, and then understand the limitations of these tools.” Read the full story here.

Vanshaj Khattar, a Ph.D. student in electrical engineering, is passionate about use-inspired research and solving real-world problems. 

“More specifically, I am interested in how we can design trustworthy reinforcement learning algorithms that are safe, robust, explainable, and can continually adapt to non-stationarity in the real world,” said Khattar, who is advised by Ming Jin.

Currently, he is working on an offline reinforcement learning (RL) problem for building energy management, where the learning agent has to learn optimal actions from a dataset without access to the environment. 

“Offline RL is hard because not all possible cases are covered inside the dataset,” Khattar said. “I am addressing this partial coverage by proposing an implicit actor-critic method for offline RL using optimization-based policies with a special robustness property to learning errors in offline RL which I am able to exploit to achieve a good performance on a multiple-building energy management problem. At the same time, I am maintaining some key aspects of interpretability which are lacking in current approaches.” 

Khattar earned a bachelor’s of technology degree in electrical and electronics engineering from Delhi Technological University, India, and earned a master’s degree in electrical engineering from Virginia Tech.

While in the master’s program, he worked on motion prediction/planning for autonomous vehicles and came across reinforcement learning methods and their huge successes in many domains such as AlphaGo. 

“However, I realized that the potential of RL methods was mostly being utilized in simulated domains, and real-world applications were still limited,” Khattar said. “This inspired me to pursue my research in building trustworthy RL algorithms that can be applied to real-world applications with safety guarantees.”

He said the opportunity to collaborate was a major factor in attracting him to Virginia Tech and the Sanghani Center.

In 2023, he has presented three papers: “Winning the CityLearn Challenge: Adaptive Optimization with Evolutionary Search under Trajectory-based Guidance” and “On Solution Functions of Optimization: Universal Approximation and Covering Number Bounds,” both at the 37^th AAAI Conference on Artificial Intelligence; and “A CMDP-within-online framework for Meta-Safe Reinforcement Learning,” at the International Conference on Learning Representations(ICLR).

Khattar is projected to graduate in 2026 and hopes to continue his research as an industry professional. 

Cyberattacks have led to substantial losses for both businesses and individual users in recent years raising an urgent need to strengthen protection against such threats,” said Wenjia Song, a Ph.D. student in computer science who is working to address the problem.

“My research focuses on machine learning application and methodology development for improving accuracy on crucial detection problems, including medical predictions and threat detection in cybersecurity, through quantitative experiments,” she said.

Song’s current project is aimed at cyber threat detection. 

“Real-world examples of such attacks include the Colonial Pipeline ransomware attack and the SolarWinds hack,” she said. “We try to detect malicious attack behaviors at an early stage in order to minimize the damage they may cause.”

Prior to entering the doctoral program, Song earned two bachelor of science degrees – in computer science and in mathematics — from Virginia Tech. 

“As a Ph.D. student, I was attracted to the Sanghani Center because of its reputation for diverse and impactful research,” she said. “I really like being part of a thriving academic community where I receive significant encouragement and support from both professors and my peers.”

Song is advised by Danfeng (Daphne) Yao.

Among her published papers are: “Subpopulation-specific Machine Learning Prognosis for Underrepresented Patients with Double Prioritized Bias Correction,” in Communications Medicine in 2022; and “Specializing Neural Networks for Cryptographic Code Completion Applications,” in IEEE Transactions on Software Engineering in 2023.

Song also presented her work on measurement of ransomware behaviors and evaluation of defenses at both the Commonwealth Cyber Initiative (CCI)/Virginia Tech Transportation Institute (VTTI) Tech Showcase in 2022 and at the CCI Symposium in 2023.

In 2022, she presented the poster “APT Detection through Sensitive File Access Monitoring” at the Network and Distributed System Security (NDSS) Symposium and the poster “Behavioral Characterization of Crypto-Ransomware and Evaluation of Defenses” at the IEEE Secure Development Conference. 

She also gave a lightning talk, “Crypto-ransomware Detection through Quantitative API-based Behavioral Profiling,” at USENIX Security 2023. 

Projected to graduate in May 2024, Song said she would like to continue her research in an industry position.

Anuj Karpatne, associate professor in the Department of Computer Science in the College of Engineering has won a five-year, $595,738 National Science Foundation Faculty Early Career Development Program CAREER award to explore a unified approach for accelerating scientific discovery using scientific knowledge and data. Karpatne is also a core faculty member at the Sanghani Center for AI and Data Analytics. Read the full story here.

The Virginia Tech Board of Visitors held its latest quarterly full-board meeting Sunday through Tuesday at the W.E. Skelton 4-H Educational Conference Center in Wirtz and at the Fralin Biomedical Research Institute at VTC in Roanoke.

Following an orientation session Sunday morning, board members engaged in a retreat to discuss issues facing Virginia Tech and higher education in general. To begin the retreat, three experts led a conversation on generative artificial intelligence (AI) and its impact on higher education and society more broadly: Naren Ramakrishnan, Virginia Tech’s Thomas L. Phillips Professor of Engineering and director of the Sanghani Center for AI and Data Analytics; Scott Hartley, co-founder and managing partner of Everywhere Ventures, a pre-seed venture capital firm, and best-selling author of “The Fuzzy and the Techie: Why the Liberal Arts Will Rule the Digital World”; and Rishi Jaitly, professor of practice and Distinguished Humanities Fellow at Virginia Tech, where he leads the Institute for Leadership in Technology. Read full story here.

Atop a new wave of support from the Fralin Life Sciences Institute, Peter Vikesland, the Nick Prillaman Professor of Civil and Environmental Engineering, is leading a research team in creating wireless sensor networks to survey microbial threats to water quality and to enable operational control and provide real-world feedback for public transparency. The project, Technology-enabled Water Surveillance and Control, reflects the “one water” concept that views water quality as important to our society, economy, and environment and requires an integrated approach to policy planning and implementation.

Lenwood Heath, professor of computer science and core faculty at the Sanghani Center for Artificial Intelligence and Data Analytics, will develop algorithms for locating sensors and designing networks for optimal benefit. Read full story here.

Academics from the University of San Francisco d’Quito in Ecuador were hosted by Aimée Surprenant, dean of the Graduate School, as part of the Future Professoriate Group from Latin America.

Among those they heard from on campus was Naren Ramakrishnan, the Thomas L. Phillips Professor of engineering at Virginia Tech, founder and director of the Sanghani Center for Artificial Intelligence and Data Analytics and director of the Amazon-Virginia Tech Initiative in Efficient and Robust Machine Learning. Read full story here.

“Start by determining the problem you desire to solve, then decide on the technology to solve it,” said Subha Madhavan, vice president and head of clinical artificial intelligence/machine learning with global biopharmaceutical company Pfizer. 

Madhavan was the keynote speaker at AI for Pediatric Health and Rare Diseases, an inter-institutional meeting of scientists and innovators co-led by Children’s National Hospital and the Virginia Tech Sanghani Center for Artificial Intelligence and Data Analytics to discuss the potential of artificial intelligence (AI) to understand pediatric health.

The pressing issue at the gathering at the Children’s National Research & Innovation Campus in Washington, D.C., involved tackling diseases, particularly cancer, in children, an area that suffers from limited treatment options and inadequate research compared with diseases affecting adults.  Read full story here.

Summer offers an opportunity for graduate students at the Sanghani Center to gain real-world experience in their research focus areas by working at major companies and labs across the country. This year these include places like Amazon AWS in Seattle, Washington; JPMorgan Chase & Co in New York City;  the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) in Cambridge, Massachusetts; Bosch in Pittsburgh, Pennsylvania; and the Intel Lab in Santa Clara, California.  

Following is a list of Sanghani Center students – where they are and what they are doing:

Satvik Chekuri, a Ph.D. student in computer science, is a natural language processing research intern working remotely with a Deloitte Audit and Assurance Data Science team in New York City. The team’s research focuses on the intersection of knowledge graphs and Large Language Models (LLMs) in the financial domain. His advisor is Edward A. Fox.

Hongjie Chen, a Ph.D. student in computer science, is a research scientist intern at Yahoo Research in Sunnyvale, California, working remotely with the advertising team. His advisor is Hoda Eldardiry.

Humaid Desai, a master’s degree student in computer science, is a software engineer intern at Ellucian in Reston, Virginia, working remotely. He is contributing to Ellucian’s SaaS-based solutions using React.js, Node.js, and AWS cloud technologies. His advisor is Hoda Eldardiry.

Jianfeng He, a Ph.D. student in computer science, is an applied scientist intern working onsite at Amazon AWS in Seattle, Washington, where he is researching text summarization. His advisor is Chang-Tien Lu.

Adheesh Juvekar, a Ph.D. student in computer science, is an applied scientist intern working on generative artificial intelligence onsite at Amazon in Boston, Massachusetts. His advisor is Ismini Lourentzou.

Myeongseob Ko, a Ph.D. student in electrical and computer engineering, is a machine learning research intern onsite at Bosch in Pittsburgh, Pennsylvania, where he is working on a diffusion model. His advisor is Ruoxi Jia.

Shuo Lei, a Ph.D. student in computer science, is a graduate research intern onsite at Intel Labs in Santa Clara, California. She is working on developing a new few-shot learning method for multi-modal object detection to lower the effort of human annotation, training effort, and domain adaptation while meeting accuracy requirements for industrial usage. Her advisor is Chang-Tien Lu.

Wei Liu, a Ph.D. student in computer science, is a business intelligence intern at Elevance Health in Indianapolis, Indiana, working remotely with the data analysis team. Her advisor is Chris North.

Amarachi Blessing Mbakwe, a Ph.D. student in computer science, is an artificial intelligence research associate intern at JPMorgan Chase & Co in New York City, working onsite. She is conducting research on natural language processing-related problems that involve applying Large Language Models (LLMs) in finance. Her advisor is Ismini Lourentzou.

Makanjuola Ogunleye, a Ph.D student in computer science is a data scientist intern at Intuit, working onsite with the company’s AI Capital team in Mountain View, California. He is contributing to key machine learning products. His advisor is Ismini Lourentzou.

Mandar Sharma, a Ph.D. student in computer science, is a Ph.D. software engineering intern at Google AI in Kirkland, Washington, where he is working onsite on integrating state-of-the-art in natural language processing to the services provided by Google’s Cloud AI platforms. His advisor is Naren Ramakrishnan.

Ying Shen, a Ph.D. student in computer science, is a research intern onsite at Apple in New York City, where she is working on diffusion models. Her co-advisors are Lifu Huang and Ismini Lourentzou.

Afrina Tabassum, a Ph.D. student in computer science, is a research intern at Microsoft in Redmond, Washington, working onsite. She is co-advised by Hoda Eldardiry and Ismini Lourentzou.

Chiawei Tang, a master’s degree student in computer science, is a software engineer intern onsite at Juniper Network in Sunnyvale, California. His work involves creating a simulator designed to emulate the data output from wired network devices such as routers and switches. This strategic initiative facilitates system scalability testing for developers and significantly mitigates the financial impact associated with the procurement of physical hardware. His advisor is Chris Thomas.

Muntasir Wahed, a Ph.D. student in computer science, is a research intern onsite at IBM Research Almaden Lab in San Jose, California, working on the development and application of foundation models. His advisor is Ismini Lourentzou.

Zhiyang Xu, a Ph.D. student in computer science, is an applied scientist intern onsite at Amazon Alexa in Sunnyvale, California, where he is working on improving dialogue systems. His advisor is Lifu Huang.  

Raquib Bin Yousuf, a Ph.D. student in computer science, is among 25 students from 19 colleges chosen to attend the Washington Post Engineering class in Washington, D.C., this summer. He is working with state of the art artificial intelligence systems to develop new technology for the Washington Post. His advisor is Naren Ramakrishnan.

Yi Zeng, a Ph.D. student in computer engineering, is a research scientist intern onsite at Meta in Menlo Park, California, working on artificial intelligence fairness, finding ways to make state of the art AI systems more robust and responsible. His advisor is Ruoxi Jia.

Jingyi Zhang, a Ph.D. student in computer science, is a graduate intern working remotely with Amgen’s Computational Biology Group within Clinical Biomarkers & Diagnostics in Thousand Oaks, California. She is taking an active role in developing a data and analytics platform as well as participating in prostate therapeutic area translational computational biology. Her advisor is Lenwood Heath.

Shuaicheng Zhang, a Ph.D. student in computer science, is a summer intern onsite at the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) in Cambridge, Massachusetts, where he is conducting research on the generative graph foundation model. His advisor is Dawei Zhou.

Xiaona Zhou, a Ph.D. student in computer science, is a University Research Association Sandia Graduate Summer Fellow at Sandia National Labs in Livermore, California. She is onsite working on anomaly detection in time series data. Her advisor is Ismini Lourentzou.