I am a researcher working at the interface of Scientific Machine Learning (SciML), Geometric Deep Learning, and Scientific Foundation Models (SciFM). My work centers on developing scalable, physics-aware machine learning frameworks for scientific data — with a focus on 3D reconstruction, computational physics, and simulation-driven learning. I build end-to-end pipelines from large scale data generation, preprocessing, training large diffusion, transformer models and experimenting with other architectures for scientific applications. I'm passionate about integrating physics priors with AI, building large scale toolkits for AI4Science applications.
Technical Expertise Scientific Foundation Models (UPT, Poseidon etc.) Geometric Deep Learning (TRELLIS, LATTE3D, etc.) Transformer-based scientific and geometric models 3D geometry processing using PyVista, Open3D, and VTK 3D computer vision (ViT, NERF, Gaussian Splatting, etc.)
Currently I am working as a Research Scientist at ANSYS
Click on the project name to directly go to it's GitHub Repository
-
Course GPT Course GPT empowers users to effortlessly create tailored mini-courses that match their specific interests and learning goals. By leveraging the capabilities of ChatOpenAI model and Langchain, this app streamlines the process of generating course content. [Demo APP]
-
Transfer learning for Malaria detection: The project demonstrates using transfer learning with MobileNetV2 to enhance malaria detection accuracy in medical images with limited training data.[Blog]
-
Physics-integrated deep learning for uncertainty quantification and reliability estimation of nonlinear dynamical systems: In this Project I have developed a Physics Integrated Variational Auto Encoder to model nonlinear and Stochastic dynamical system. The main idea to use and ODE solver in the decoder which will solve partial linear system additively augmented with output of MLP which will take care of remaining physics. Based on the result obtained it can be said that this model is suitable for system with parametric uncertaininty and modelling discrepencies and especially is the cases where large number of measurement samples are required. [Research Paper]
-
How to build a AI-based Chatbot in Python: The project demonstrates building a Python chatbot using ChatterBot, NLTK, and TensorFlow, covering types of chatbots, data preprocessing, and response generation.[Blog]
-
PDF summarization using Pegasus: The project demonstrates using the Pegasus model to summarize large PDF documents, utilizing PyPDF2 for text extraction and building a web app with Streamlit for easy user interaction and deployment. [Blog]
