The Center for Socially Responsible AI will host a graduate student rump session, which will feature four short talks by Penn State doctoral students. This event is free and open to the Penn State community.
About the Talks
"The Cure Is Timing: How AI Voice Biomarkers Open the Treatment Window in Alzheimers" - Kevin Mekulu, College of Engineering
We’re developing AI to flag Alzheimer’s years before memory loss begins, using just a 60-second voice sample. By opening the treatment window earlier, this technology could change how we fight one of the world’s toughest diseases.
"Zero Shot Diagnosis for Rare Conditions" - Ishan Shivansh Bangroo, College of Information Sciences and Technology
Zero-shot learning lets a model recognize new conditions without task-specific training data. A demonstration of the same with public data and simple baselines to show what works, where it breaks, and how to check safety, fairness, and privacy in clinical use will be performed. The application of ZSL within healthcare diagnostics is an emerging area of interest, focusing on its capacity for facilitating detection in the absence of pre-existing training data.
"Being Stable and Reliable under Twists: Robustness of GraphRAG Systems" - Tianyang Zhao, College of Information Sciences and Technology
A RAG system uses external knowledge bases to be up-to-date, and a GraphRAG system further improves this by employing a graph for knowledge representation. However, few studies investigate how robust GraphRAG is. In this research, exploratory experiments have been performed, and preliminary results show that the model is robust even when the semantics of the extracted knowledge in the graph have been changed.
"Echoes of Automation: The Increasing Use of LLMs in Newsmaking" - Abolfazl Ansrai, College of Information Sciences and Technology
The rapid rise of Generative AI (GenAI), particularly LLMs, poses concerns for journalistic integrity and authorship. This study examines AI-generated content across over 40,000 news articles from major, local, and college news media, in various media formats. Using three advanced AI-text detectors (e.g., Binoculars, Fast-Detect GPT, and GPTZero), we find substantial increase of GenAI use in recent years, especially in local and college news. Sentence-level analysis reveals LLMs are often used in the introduction of news, while conclusions are usually written manually. Linguistic analysis shows GenAI boosts word richness and readability but lowers formality, leading to more uniform writing styles, particularly in local media.
About the Speakers
Kevin Mekulu, a Penn State Ph.D. candidate and Forbes 30 Under 30 honoree in Healthcare, is advancing AI speech and eye-tracking biomarkers to transform dementia care. He is the founder of DementiAnalytics, a startup at the intersection of AI, healthcare, and aging.
Ishan Shivansh Bangroo is a graduate researcher at Penn State University in the College of Information Sciences and Technology. He works at the intersection of health informatics and human computer interaction, building simple, privacy aware tools for mental health and clinical decision support.
Tianyang Zhao is a Ph.D. candidate in Informatics at Penn State. His research interests include natural language processing (NLP), explainable AI, knowledge representation and reasoning. He has worked on multiple fields of research: NLP, privacy, trustworthiness of language models, and convolutional neural network for image processing. Prior to the Ph.D. program, he obtained his B.S. in Computer Science and his M.S. in Computer Science and Engineering also at Penn State.
Abolfazl Ansari is a Ph.D. student in the College of Information Sciences and Technology at Penn State University, where he is advised by Professor Dongwon Lee. He began his doctoral studies in January 2025. He received his B.Sc. in Computer Science in 2023. His research interests include fact verification and reasoning in large language models (LLMs) and vision-language models (VLMs), with a particular focus on scientific domains.
About the Young Achievers Symposium
The Young Achievers Symposium highlights early career researchers in diverse fields of AI for social impact. The symposium series seeks to focus on emerging research, stimulate discussions, and initiate collaborations that can advance research in artificial intelligence for societal benefit. All events in the series are free and open to the public unless otherwise noted. Penn State students, postdoctoral scholars, and faculty with an interest in socially responsible AI applications are encouraged to attend.