Research
I am interested in the area of representation learning. More recently, I have developed an interest in diffusion models (subjects include alignment, test-time scaling, controlled generation).
Please refer to my Google Scholar profile for details on the publications I have been fortunate to be a part of.
Conference tutorials
- Practical Adversarial Robustness in Deep Learning: Problems and Solutions (CVPR’21)
- Foundational Robustness of Foundation Models (NeurIPS’22)
- All Things ViTs: Understanding and Interpreting Attention in Vision (CVPR’23)
- (Upcoming) Post-Training Diffusion Models: Enhancing Capabilities, Control, and Alignment (ECCV’26)
Invited talks, demos, etc.
| Talk | Venue | Date | Links |
|---|---|---|---|
| SoTA Diffusion Models with 🧨 diffusers | IBM Research | October 17, 2023 | slides, recording |
| SoTA Diffusion Models with 🧨 diffusers | The Dyson Robotics Lab, Imperial College London | 2023 | slides, recording |
| SoTA Diffusion Models with 🧨 diffusers | Department of Statistics, University of Oxford | 2023 | slides, recording |
| 🧨 diffusers for research | VAL, Indian Institute of Science (IISc) | June 12, 2023 | slides |
| Controlling Text-to-Image Diffusion Models: Assorted Approaches | BigMAC ICCV Workshop | 2023 | slides, recording |
| Controlling Text-to-Image Diffusion Models: Assorted Approaches | UCL | June 2024 | — |
| Controlling Text-to-Image Diffusion Models: Assorted Approaches | Texas A&M University | Sept 2024 | slides |
| Controlling Text-to-Image Diffusion Models: Assorted Approaches | UC Berkeley | October 2024 | slides, recording |
| Controlling Text-to-Image Diffusion Models: Assorted Approaches | ICDMAI’25 | 2025 | slides |
| Demo of 🧨 diffusers | ICCV 2023 | 2023 | Tweet |
| A talk on diffusion models | ETH Zurich | May 06, 2024 | slides |
| Transformers in Diffusion Models for Image Generation and Beyond | CS25 v5, Stanford | May 27, 2025 | slides, recording |
| State of Open Video Generation Models | Indian Institute of Science (IISc) | Sept 17, 2025 | slides |
| Optimizing the Full Stack for Generative Image and Video Models | CBMM MIT | Sept 22, 2025 | slides, recording |
| Controllable Video Diffusion for Length 📹 | LongVid Workshop (ICCV’25) | Oct 20, 2025 | slides |
A little shoutout on the CS25 v5 Stanford talk from Sander Dieleman.
For regular talks, refer here.
Teaching assistance
Served as a TA for Full Stack Deep Learning’s 2022 cohort.
Reviewing
- Conferences: ICLR’26, ACL’26, CVPR’26, NeurIPS’25, ICCV’25, ICML’25, CVPR’25, ICLR’25, NeurIPS’24, AAAI’23, ICASSP’21 (sub-reviewer).
- PyTorch Conference Europe 2026
- Workshops: UDL workshop (ICML’21).
- Journals: TMLR, Artificial Intelligence (Elsevier), IEEE Access.
Misc
- Released a dataset for large-scale multi-label text classification (joint work with Soumik Rakshit).
- Exploration on instruction-tuning Stable Diffusion.