Sandeep Nagar ☕️

About Me

Hi 👋 I am a postdoctoral researcher at the Institute for Advanced Study (IAS), TU Munich, working in the AI-IDT Lab with Prof. Benedikt Wiestler and Prof. Anke Meyer-Baese (Florida State University). I completed my PhD at the Machine Learning Lab, IIIT-Hyderabad, advised by Prof. Girish Varma. My research focuses on probabilistic generative models—especially normalizing flows—theoretical machine learning, and deep learning, with applications in computer vision and medical imaging.

I spent a semester at Samsung Research with Dr. Sathya Veera Reddy Dendi and Dr. Pravin Nair on generative models for image super-resolution, and previously interned at:

  • CVR Lab, University of Illinois Urbana-Champaign, with Prof. Narendra Ahuja, in collaboration with Dr. David Beiser and Dr. David Chestek at the University of Illinois College of Medicine.
  • School of Mathematics and Statistics, University of New South Wales, with Prof. Rohitash Chandra and Dr. Ehsan Farahbakhsh (School of Geosciences, The University of Sydney).

I hold a B.Tech in Computer Science & Engineering from Harcourt Butler Technical University, Kanpur. I am from Greater Noida, India. Outside research, I enjoy building ML systems and reading; my book list is on Goodreads.

News and Updates

Download CV
Interests
  • Probabilistic Generative Models
  • Theoretical Machine Learning
  • Computer Vision
  • Medical Imaging
  • AI4Health, Science
Education
  • PhD in Computer Science

    IIIT-Hyderabad, India

  • B.Tech in Computer Science & Engineering

    Harcourt Butler Technological University - Kanpur, India

Recent Publications

Recent papers below. See all publications or Google Scholar.

(2026). MRIComp4Flow: Compression of 3D Brain MRI for Training Multi-Modal Generative Models. Simulation and Synthesis in Medical Imaging (SASHIMI), MICCAI 2026 Workshop.
(2026). TumorFlow: Physics-Guided Longitudinal MRI Synthesis of Glioblastoma Growth. 29th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2026).
(2025). Fast & Efficient Normalizing Flows and Applications of Image Generative Models. PhD thesis, International Institute of Information Technology, Hyderabad.
(2025). A Biophysically-Conditioned Generative Framework for 3D Brain Tumor MRI Synthesis. BraTS-Lighthouse Challenge, 28th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2025).
(2025). Leveraging high-spin DFT features for prediction of spin state gaps in 3d transition metal complexes. Physical Chemistry Chemical Physics.
(2025). Private IDD: Data Anonymization in the Indian Driving Dataset using Inpainting. In preparation.
(2025). Inverse-Flow: Parallel Backpropagation for Inverse of a Convolution with Application to Normalizing Flows. The 28th International Conference on Artificial Intelligence and Statistics (AISTATS 2025).
(2024). R2I-rPPG: A Robust Region of Interest Selection Method for Remote Photoplethysmography to Extract Heart Rate. arXiv preprint.