Research

A curated collection of my research, organised by track.

UG Thesis

My undergraduate thesis on generative models for unsupervised speech time-scale modification, under the joint supervision of Prof. Prasanta Kumar Ghosh (SPIRE Lab, IISc) and Prof. Niteesh Sahni (SNIoE) — won 2nd Prize for Best UG Thesis.

Thesis PosterRead →
Speech Time Scale Modification with GANsRead →
Speech TSM using GANs - PresentationRead →
Statistics for Generative ModelsRead →
Denoising Diffusion Probabilistic Models NotesRead →
Generative Models: A Mathematical OverviewRead →
6 resourcesView Track →

PhD Research Courses

I completed 5 PhD-level courses during my undergraduate degree. These are the resources and notes I created while completing them.

  1. Advanced Deep Learning
  2. Advanced Computer Vision
  3. Special Topics in AI
  4. Measure & Integration
  5. Stochastic Processes
Latent Diffusion Model Paper PresentationRead →
CSD 722: Depth Conditioned Video GenerationRead →
Contrastive Learning: SimCLR & I-JEPARead →
Variational Autoencoders (VAEs)Read →
Vision Transformer (ViT)Read →
Statistics for Generative ModelsRead →
Lecture on Flow MatchingRead →
Denoising Diffusion Probabilistic Models NotesRead →
8 resourcesView Track →

Alignment & Safety in T2I and T2V Models

Working on safety alignment of Text-to-Image & T2V diffusion and flow matching models using a neurosymbolic approach called scene graphs.

TRCE Paper PresentationRead →
CSD 722: Depth Conditioned Video GenerationRead →
2 resourcesView Track →

Seminar and Lecture Notes

From my UG Seminar course, where we were taught how to write reports, papers, and give presentations — these are the resources and notes from that coursework.

Principal Component AnalysisRead →
Cross Validation TechniquesRead →
Sequential Models: RNNs OverviewRead →
Neural Networks: Foundations and ArchitecturesRead →
4 resourcesView Track →

Interpretability & Theory of DL

Developing attribution techniques (Integrated Gradients, Manifold IG, Guided IG) towards neural network interpretability, extending to sequential models and LLMs.

Explainable AI: Attribution TechniquesRead →
Theory of LLMs — Notion NotesRead →
2 resourcesView Track →
Calendly - Let's meet!