Kempner Institute Welcomes Spring 2025 Undergraduate Student Researchers
Eighteen undergraduate students receive KURE awards to undertake intelligence-focused research projects
A group of spring 2025 KURE undergraduate researchers pose for a photo at the Kempner Institute during the program orientation in February 2025.
Photo credit: Lani O'Donnell
Cambridge, MA – The Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard is pleased to announce the spring 2025 recipients of the Kempner Undergraduate Research Experience (KURE). KURE awards Harvard undergraduate students funding for term-time research supervised by Kempner-affiliated faculty during the fall and spring semesters of the academic year.
Student research projects investigate the foundations of intelligence, including mathematical and computational models of intelligence, cognitive theories of intelligence, and the neurobiological basis of intelligence, as well as applications of artificial intelligence from a scientific or engineering perspective.
In addition to its term-time undergraduate research program, the Kempner offers a 10-week residential summer program called KRANIUM, providing a small cohort of undergraduates with a formative research experience under the supervision of a Kempner-affiliated faculty member.
The spring 2025 KURE recipients (listed below) represent the third cohort of undergraduates to participate in the Kempner’s term-time undergraduate research program. More information about KURE and KRANIUM can be found on the Kempner Institute website.
Spring 2025 KURE Award Recipients
| Student | Concentration | Supervisor/Mentor | Project title |
|---|---|---|---|
| Rafay Azhar ’25 | Computer Science | Supervisor: Mengyu Wang | Optimizing Vision-Language Models for Egocentric Data to Assist the Visually Impaired |
| Joey Bejjani ’26 | Computer Science | Supervisors: Sham Kakade and Yilun Du | Adaptive Multiagent Debate With Latent Space Reasoning |
| Drake Du ’26 | Statistics and Computer Science | Supervisor: Mengyu Wang | Time-SAW: Time-Smoothing Adaptive Weighting for Flow-Based Diffusion Model |
| David Ettel ’26 | Mathematics | Supervisor: Melanie Weber | Doe Approximate Equivariance Matter at Scale |
| Emma Finn ’26 | Math and Classics with Concurrent AM in Statistics | Supervisor: Demba Ba; Mentors: Andy Keller and Manos Theodosis | From Noise to Novelty: The Origins of Creativity in Attention Based Diffusion Models |
| Ryland Gross ’26 | Mathematics | Supervisor: Nada Amin | Machine-Made Mathematics: Applying LLMs to Lean4 for Automated Proof Generation |
| Ely Hahami ’27 | Mathematics | Supervisor: Haim Sompolinsky; Mentor: Xu Pan | Memory and Knowledge Injection in Gated Large Language Models |
| Bright Liu ’26 | Mathematics and Computer Science | Supervisor: Sham Kakade; Mentor: Rosie Zhao | Investigating the Tradeoff Between Verification and Generation in Scaling Test-Time Compute |
| Jasmine Liu ’28 | Computer Science | Supervisor: Jie Yang | Mitigating Hallucinations in Medical LLMs with Knowledge-Enhanced Reasoning |
| Adithya Madduri ’27 | Molecular & Cellular Biology and Statistics | Supervisor: Bernardo Sabatini; Mentor: Kimberly Reinhold | Automated Behavioral Analysis of Skilled Forelimb Reaching Behaviors in Mice |
| Teodor Malchev ’27 | Computer Science | Supervisor: Nada Amin | Using Linguistics to Evaluate and Improve LLM |
| Sean Meng ’26 | Neurobiology | Supervisor: Bernardo Sabatini; Mentor: Kevin J Mastro | Contrastive Learning and Transformer-Based Multimodal AI for Predicting Cognitive Resilience and Decline in Aging Mice |
| Aoi Otani ’25 | Integrative Biology | Supervisor: Nada Amin; Mentor: Morgan Talbot | Mitigating Catastrophic Forgetting and Mode Collapse in Continual Text-to-Image Diffusion via Latent Replay |
| Purab Seth ’26 | Computer Science | Supervisor: Wilka Carvalho | Multi-agent Reinforcement Learning for Dynamic Role |
| Lillian Sun ’26 | Computer Science | Supervisors: Sham Kakade and Yilun Du | Optimizing Inter-Model Communication in Multi-Agent Systems |
| Mira Yu ’27 | Computer Science and Government | Supervisor: Finale Doshi-Velez | AI for Humanitarian Crisis Negotiation and Beyond |
| Eric Xu ’28 | Undeclared | Supervisor: Venkatesh Murthy | Using Clique Topology and Co-Occurrence Statistics to Determine Olfactory Geometry and Parameters |
| Richard Zhu ’26 | Statistics | Supervisor: Marinka Zitnik; Mentor: Shanghua Gao | RL-Inspired Framework for Uncertainty-Aware Agentic Reasoning |
About the Kempner Institute
The Kempner Institute seeks to understand the basis of intelligence in natural and artificial systems by recruiting and training future generations of researchers to study intelligence from biological, cognitive, engineering, and computational perspectives. Its bold premise is that the fields of natural and artificial intelligence are intimately interconnected; the next generation of artificial intelligence (AI) will require the same principles that our brains use for fast, flexible natural reasoning, and understanding how our brains compute and reason can be elucidated by theories developed for AI. Join the Kempner mailing list to learn more, and to receive updates and news.
PRESS CONTACT:
Deborah Apsel Lang | (617) 495-7993
