Prateik Sinha

Machine Learning Engineer @ Dassault Systemes
Researcher @ The MINT Group & Roychowdhury Group at UCLA

Hello! My name is Prateik Sinha, I am a machine learning engineer at Dassault Systemes. I work on 3D computer vision and natural language processing for SolidWorks.

I'm researching AI for atmospheric sciences with Professor Aditya Grover and AI for neuroscience with Professor Vwani Roychowdhury at UCLA. My research interests range from AI for Science to interpretability, computer vision, foundation models, and generative AI.

I recently graduated from UCLA with majors in Mathematics of Computation and Statistics and Data Science. During this time I interned as a ML engineer at Dassault Systemes and as a data scientist at Zelis. I also served as the projects director of ACM AI at UCLA.

News

  • Jan 2025: Accepted to the Master's program in the Machine Learning Department at Carnegie Mellon University, starting Fall 2025
  • 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 Systemes
  • Mar 2024: Graduated from UCLA with a B.S. in Mathematics of Computation and Statistics and Data Science

Publications

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

Mini-Seizures: Novel Interictal iEEG Biomarker Capturing Synchronization Network Dynamics at the Epileptogenic Zone
Tonmoy Monsoor, Sotaro Kanai, Atsuro Daida, Naoto Kuroda, Prateik Sinha, Shingo Oana, Yipeng Zhang, Lawrence Liu, Gaurav Singh, Chenda Duan, Myung Shin Sim, Aria Fallah, William Speier, Eishi Asano, Vwani Roychowdhury, Hiroki Nariai In AES 2024 Conference
Under Review at Nature Neuroscience
[Paper] [Poster]

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]

Resume

Last updated: 27 Apr 2025