Prateik Sinha

M.S. Machine Learning @ Carnegie Mellon University
Research Intern @ Sakana AI

Hello! My name is Prateik Sinha, I am a Master's student in the Machine Learning Department at Carnegie Mellon University. My research interests range from AI for Science to foundation models, generative AI, computer vision and interpretability. I'm currently researching AI for molecular dynamics with Professor Andrej Risteski.

Previously, I was a machine learning engineer at Dassault Systèmes where I worked on 3D computer vision for SolidWorks. Before that, I graduated from UCLA with majors in Mathematics of Computation and Statistics and Data Science. During this time I researched AI for atmospheric sciences with Professor Aditya Grover and AI for neuroscience with Professor Vwani Roychowdhury. I also served as the projects director of ACM AI at UCLA.

I am applying for PhD programs for Fall 2027. If you are interested in my research, please feel free to reach out to me at prateiks@cs.cmu.edu

News

  • May 2026:Started as a Research Intern at Sakana AI
  • Apr 2026:Two papers on VLMs for seizure semiology have been accepted: one as an ICML 2026 Spotlight and one to IEEE EMBC 2026
  • Jan 2026:Our work on pathological states in organoid neuronal networks has been accepted to ICASSP 2026
  • Aug 2025:Started as a Master's student in the Machine Learning Department at Carnegie Mellon University
  • Oct 2024:AtmosArena has been accepted to two NeurIPS workshops
  • Aug 2024:Our paper on using synchronization networks to identify epileptogenic zones from iEEG recordings has been accepted by the American Epilepsy Society (AES 2024)
  • Apr 2024:Started as an ML engineer working on Solidworks at Dassault Systèmes
  • Mar 2024:Graduated from UCLA with a B.S. in Mathematics of Computation and Statistics and Data Science

Publications


2026

Seizure-Semiology-Suite(S³): A Clinically Multimodal Dataset, Benchmark, and Models for Seizure Semiology Understanding
Lina Zhang, Jiarui Cui, Tonmoy Monsoor, Peizheng Li, Xinyi Peng, Chong Han, Prateik Sinha, Siyuan Dai, Jessica Nichole Pasqua, Colin M McCrimmon, Weiting Liu, Hailey Marie Miranda, Bing Hu, Xiangting Wu, Tengyou Xu, Chunhan Li, Jiaye Tian, Jiarui Tang, Detao Ma, Lingye Kong, Junnan Lyu, Jungang Li, Yan Zan, Junhua Huang, Rajarshi Mazumder, Vwani Roychowdhury
ICML 2026 (Spotlight)

Can Multimodal Large Language Models Understand Pathologic Movements? A Pilot Study on Seizure Semiology
Lina Zhang, Tonmoy Monsoor, Prateik Sinha, Mehmet Efe Lorasdagi, Chong Han, Peizheng Li, Yuan Wang, Jessica Pasqua, Colin McCrimmon, Rajarshi Mazumder, Vwani Roychowdhury
IEEE EMBC 2026

Interictal Mini-Seizures: Recurrent Neuronal Synchronization Events Driven by the Epileptogenic Zone
Tonmoy Monsoor, Sotaro Kanai, Prateik Sinha, Atsuro Daida, Naoto Kuroda, Shingo Oana, Lina Zhang, Lawrence Liu, Gaurav Singh, Yipeng Zhang, Chenda Duan, Shaun A Hussain, Raman Sankar, Aria Fallah, Myung Shin Sim, William Speier, Richard J Staba, Jerome Engel Jr., Eishi Asano, Vwani Roychowdhury, Hiroki Nariai
medRxiv preprint
[Paper]


2025

Time-Resolved Neuronal Network Dynamics Distinguish Pathological States in Organoid Models
Colin M. McCrimmon*, Prateik Sinha*, Qing Cao*, Tonmoy Monsoor*, Kartik Sharma, Mehmet Yigit Turali, Ranmal A. Samarasinghe, Vwani Roychowdhury
ICASSP 2026
[Paper]

Automated Seizure Classification Using Multimodal Large Language Models
Lina Zhang, Richard Jiang, Tonmoy Monsoor, Jessica Nichole Pasqua, Colin M. McCrimmon, Prateik Sinha, Kartik Sharma, Muayad Alzuabi, Victor Morales, Hailey Marie Miranda, Chaya Manjeshwar, Vwani Roychowdhury, Rajarshi Mazumder
medRxiv preprint
[Paper]


2024

AtmosArena: Benchmarking Foundation Models for Atmospheric Sciences
Tung Nguyen, Prateik Sinha, Advit Deepak, Karen A. McKinnon, Aditya Grover
NeurIPS 2024 Workshop on Foundation Models for Science (FM4Science)
NeurIPS 2024 Workshop on Tackling Climate Change with Machine Learning (CCAI)
[Paper] [Leaderboard] [Code]

Projects

  • people2vec (LA Hacks 2023: 3rd Place Overall)
    • A web app that matches you with people of similar interests by doing a similarity search on embeddings of your YouTube watch histories.
    [GitHub] [Devpost]

  • WikiSafe (HackMIT 2022: 2nd Place, Blockchain for Society)
    • A wiki that uses the Ethereum blockchain to create a public, immutable record of all the edits made to it to prevent vandalism. Also has a bunch of built in ML models to make editing easier.
    [GitHub]

  • KaoGPT (UCLA ECE C147 Final Project)
    • Comparing the performance of different text generation models.
    [Report]

Links

Resume

© Copyright 2026 Prateik Sinha. Last updated: 2 May 2026