Srikar Yellapragada

I am a PhD student in the Computer Science department at Stony Brook University, advised by Dimitris Samaras. My research is focused on Generative models for Computer Vision. Before this, I was a Software Engineer at Bloomberg LP, where our team built an ETL pipeline for the ingestion of third-party data.

In 2020, I obtained my Master's in Computer Science from NYU, where I worked with Kyunghyun Cho's group on Similarity of Neural Networks, and interned at IBM Watson Health.

Previously, I obtained a B.Tech in Electrical Engineering from Indian Institute of Technology, Hyderabad, where I worked with Sumohana Channappayya on Image Processing. I interned at Video Analytics Lab, IISc Bangalore.

In my free time, I enjoy playing video games and reading fantasy novels. I'm a big fan of strategy games, such as Dota 2 and Age of Empires 2.

News

Publications / Pre-prints

ZoomLDM: Latent Diffusion Model for multi-scale image generation
Srikar Yellapragada*, Alexandros Graikos*, Kostas Triaridis, Prateek Prasanna ,Rajarsi Gupta, Joel Saltz, Dimitris Samaras
CVPR, 2025
Paper / Large image viewer

Multiscale diffusion model for histopathology and satellite imagery.

Leveraging Registers in Vision Transformers for Robust Adaptation
Srikar Yellapragada, Kowshik Thopalli , Vivek Narayanaswamy, Wesam Sakla, Yang Liu, Yamen Mubarka, Dimitris Samaras , Jayaraman J. Thiagarajan
ICASSP, 2025
Paper

Registers make ViTs robust

Learned Representation-Guided Diffusion Models for Large-Image Generation
Alexandros Graikos*, Srikar Yellapragada*, Minh-Quan Le, Saarthak Kapse , Prateek Prasanna , Joel Saltz, Dimitris Samaras
CVPR, 2024
Paper / Project Page / Code

We condition latent diffusion models with SSL embeddings and generate large images in histopathology and satellite imagery.

∞-Brush: Controllable Large Image Synthesis with Diffusion Models in Infinite Dimensions
Minh-Quan Le* , Alexandros Graikos* , Srikar Yellapragada, Rajarsi Gupta , Joel Saltz , Dimitris Samaras
ECCV, 2024
Paper / Project Page /

We introduce the first conditional diffusion model in functional space.

PathLDM: Text Conditioned Latent Diffusion Model for Histopathology
Srikar Yellapragada*, Alexandros Graikos*, Prateek Prasanna, Tahsin Kurc, Joel Saltz, Dimitris Samaras
WACV, 2024
Paper / Project Page / Code

We build a text-conditioned LDM for histopathology using GPT-summarized text reports and CLIP embeddings.

Conditional Generation from Unconditional Diffusion Models using Denoiser Representations
Alexandros Graikos*, Srikar Yellapragada*, Dimitris Samaras
BMVC, 2023
Paper / Code / Poster

We condition unconditional models in limited data scenarios using an auxiliary network built upon denoiser representations.

Are the Proposed Similarity Metrics Also a Measure of Functional Similarity?
Manikanta Srikar Yellapragada
Master's Thesis, 2020
Paper

Short answer: NO.
Existing representation similarity metrics cannot fully capture the output (functional) similarity of a neural network.

Deep Learning Based Detection of Acute Aortic Syndrome in Contrast CT Images
Manikanta Srikar Yellapragada, Yiting Xie, Benedikt Graf, David Richmond, Arun Krishnan, Arkadiusz Sitek
ISBI, 2020
Paper
Automatic Diagnosis of Pulmonary Embolism Using an Attention-Guided Framework: A Large-Scale Study
Luyao Shi, Deepta Rajan, Shafiq Abedin, Manikanta Srikar Yellapragada, David Beymer, Ehsan Dehghan
MIDL, 2020
Paper
Optical Character Recognition (OCR) for Telugu: Database, Algorithm and Application
Konkimalla Chandra Prakash, Y.M.Srikar, Gayam Trishal, Souraj Mandal, Sumohana S. Channappayya
ICIP, 2018
Paper / Code