PhD candidate in Electrical & Computer Engineering at Purdue University, advised by Prof. Joseph Makin.

My research focuses on deep generative modeling, particularly diffusion and score-based methods, with applications to inverse problems and neural data modeling. I am broadly interested in generative modeling (diffusion, latent, and related continuous-time approaches), multi-modal learning, and computational imaging, and in developing principled methods that bridge theory and real-world deployment.

Prior to my PhD, I worked for over five years as an Instrumentation & Control Engineer, where I independently maintained and upgraded distributed control systems and led a team of six technicians. This experience strengthened my ability to execute high-stakes technical work with precision and rigor.

📢 Recent Updates

• 🔥 New arXiv paper (2025):
  Solving Diffusion Inverse Problems with Restart Posterior Sampling

• 📰 PLOS Computational Biology (2025):
  Deep Neural Networks Explain Spiking Activity in Auditory Cortex

• 🎓 Teaching Assistant — ECE-60131: General Models (Fall 2025)

🔬 Publications

• Solving Diffusion Inverse Problems with Restart Posterior Sampling
  arXiv, 2025
  arXiv

• Deep Neural Networks Explain Spiking Activity in Auditory Cortex
  PLOS Computational Biology, 2025
  Paper

🎤 Conferences

• COSYNE 2023 — Montreal, Canada
  Poster: Understanding Auditory Cortex with Deep Neural Networks

✍️ Writing

• How Neural Networks Learn: A Probabilistic Viewpoint
  Read on Medium

• Pretraining wav2vec2 Using Hugging Face Trainer API
  Read on Medium

🎯 Research Interests

• Diffusion and score-based generative modeling
• Inverse problems and probabilistic inference
• Multi-modal learning
• Computational imaging
• Neural representation modeling

🌱 Outside Research

• Reading: Investing, economics, business
• Sports: Cricket, badminton