MIT SuperUROP

Read about the exciting work being done by SuperUROP Scholar Titus Roesler in the February 24, 2025 issue of MIT NEWS. More information about SuperUROP can be found at https://superuop.mit.edu

Arthur Liang, MIT SuperUROP Scholar is exploring the use of Large Language Models to accelerate research of proteins. MIT EECS | Takeda Undergraduate Research and Innovation Scholar Supervisor:  Prof. Manolis Kellis Research Title: Substructure-aware Protein Representation Learning for Reasoning Over Proteins with Large Language Models   We focus on harnessing the high-level reasoning capabilities of large language models to accelerate the scientific discovery of proteins. In particular, we train large language models to utilize protein embeddings generated by state-of-the-art protein sequence and structure encoders. By infusing a large language model with the ability to directly reason over this richer representation of protein function, we produce a model that has both the flexibility and generalizability of a natural language interface as well as the grounding in fundamental biology that comes from protein sequence and structure rather than arbitrary gene names. With this model, scientists will be able to answer complex queries over the protein space as well as engage in hypothesis generation. I am participating in SuperUROP to deepen my research experience and contribute to cutting-edge advancements in AI. With my background in machine learning, particularly in representation learning and computational neuroscience, I hope to explore new methodologies, collaborate with experts, and refine my problem-solving skills. https://lnkd.in/eWegAvj4 Learn more about SuperUROP here: https://superurop.mit.edu

SuperUROP Scholar Mishael Quraishi named 2025 Churchill Scholar Mishael Quraishi is majoring in material sciences and archeology, with a minor in ancient and medieval studies. https://lnkd.in/e5QcAxnu Photo: Kristie Rae

Jinhee Won, SuperUROP Student MIT EECS | Lincoln Laboratory Undergraduate Research and Innovation Scholar Research Title: Exploring Computer Vision and Machine Learning Models to Better Predict Infections in Surgical Wounds   Wound infections, particularly Surgical Site Infections (SSIs), represent a major healthcare challenge globally, especially in low-resource settings. This project aims to develop a mobile-based machine-learning model for accurately detecting SSIs from wound images by utilizing both RGB and thermal data. Building on previous research, I will explore and optimize various machine learning models, incorporating advanced techniques such as feature engineering and transfer learning. I will also evaluate the performance of these models across different computational platforms, including laptops, servers, and Android devices. The ultimate goal is to create a robust, scalable model that can be deployed widely, helping to reduce the incidence of SSIs and improve patient care worldwide.   I am participating in SuperUROP to gain in-depth research experience and apply my knowledge in machine learning to a challenging problem in healthcare. My background in computer science, particularly in image processing and AI, has prepared me well for this project. I’m excited to learn more about the research process, refine my technical skills, and work toward publishing a paper. Supervisor Richard Fletcher Learn more about SuperUROP at superurop.mit.edu

SuperUROP Scholar Lara Ozkan Named a 2025 Marshall Scholar Congratulations to MIT senior Lara Ozkan on being selected as a 2025 Marshall Scholar! Lara, majoring in computer science and molecular biology, will pursue graduate studies in the U.K. As a SuperUROP Eric and Wendy Schmidt Center Research and Innovation Scholar, Lara conducts groundbreaking research on sex-specific differences in Alzheimer's disease. Learn more about Lara's SuperUROP journey here: https://lnkd.in/eX6u9nJd Discover more about the SuperUROP program: superurop.mit.edu Photo Credit: Ian MacLellan

SuperUROP Student Research Spotlight Rishab X. Parthasarathy MIT EECS | Citadel Undergraduate Research and Innovation Scholar Research Supervisor: Prof. Daniel Sanchez Research Title:  An FPGA-Based Spatial Accelerator for Sparse Iterative Solvers While current hardware accelerators, like GPUs, excel on standard matrix operations, they fail to exploit one key matrix property-sparsity-when matrices consist of mostly zeros. One such application of sparsity is reducing the computational cost of solving massive systems of linear equations, which are found in scientific computing from circuits to urban planning. Hence, in this project, our work aims to implement a custom spatial accelerator for solving these sparse linear systems. We will first develop processor elements for sparse matrix-vector multiplies and triangular solves, which will be connected via a custom networking protocol. Then this system will then be transformed into a real-world implementation of FPGAs, which we will compare to the current state-of-the-art accelerators. Through this SuperUROP, I want to gain experience working with practical hardware applications. Drawing from my background in ML and ML Systems, I want to transfer the theoretical knowledge I acquired in Computer Systems Architecture (6.5900) to learn how to build optimized real-world accelerators for scientific computing applications. I’m very excited to expand my knowledge of digital hardware design and hopefully be able to publish my work. Learn more about SuperUROP at https://superurop.mit.edu

William Young Yang MIT EECS | Boeing Undergraduate Research and Innovation Scholar   Research supervisor:  Daniela L. Rus Research Title: Multiagent Flight Coordination Using Natural Language We consider the problem of building an effective quadrotor flight coordination model using natural language inputs. With recent advances in 3D rendering techniques such as Gaussian Splatting, training quadrotor flight vehicles in virtual environments such as physics engines has gained prevalence. Through randomization of task relevant objects and the surrounding virtual environment, previous research work has shown training in these virtual training environments transfers well to real world drone tasks. I’m excited to join SuperUROP and continue building my UROP experience as an aspiring future ML researcher. SuperUROP’s emphasis on writing and diligent research reports will help develop important communication skills I’ll need in my future work. I’m excited to continue learning about 3D rendering while also crafting a final report to show my findings. Learn more about SuperUROP at https://superurop.mit.edu

2024-2025 SuperUROP Scholar Janvi Huria MIT EECS | Takeda Undergraduate Research and Innovation Scholar  Research Supervisor: Prof. Sangeeta Bhatia Research Title: Early Detection of Cholangiocarcinoma with Diagnostic Nanoparticles Cholangiocarcinoma (CCA) is a deadly bile duct cancer that can be challenging to distinguish from benign fibrotic conditions. To improve detection, we developed activatable zymography probes (AZPs), peptide-based agents that bind to cancer cells after being cleaved by dysregulated proteases. I have screened 29 AZPs in a murine CCA model and identified 5 with significantly higher binding to CCA tumors compared to fibrotic lesions. Now, through this project, I will determine the specific proteases involved in AZP cleavage, develop a new peptide that requires two cleavage events for activation, and test an enhanced AZP6 for PET imaging. Additionally, I will improve our quantification pipeline with new scripts for detailed pixel-by-pixel colocalization analysis. I am participating in SuperUROP because I want to further my research interests at the intersection of biological engineering and computational techniques. I am interested in developing new tools to address clinical difficulties in diagnosing cancer. I have enjoyed and am excited to expand my work in nanoparticle engineering while developing new analytical protocols. Learn more about the Super UROP Program at superurop.mit.edu Join us at the 2024-2025 SuperUROP showcase on December 5, 3-5 PM, MIT Stata Center Student Street. Register here: https://lnkd.in/evwQjUi9

Do you dread writing, MIT undergraduate Rachel Yang provides insight that may help.

2024-2025 SuperUROP Scholar Shruthi Ravichandran