About Me

Hello, I am Tushar Kataria, a PhD candidate at University of Utah, Utah in School of Computing. I am in Scientific Computing and Imaging Institute advised by Prof. Shireen Elhabian.

Research Interests

My broader research interests lie in image processing, medical image processing, deep learning, and computer vision. Specifically, I focus on semantic segmentation, instance segmentation, and domain adaptation challenges in medical imaging datasets. I am also interested in statistical shape modeling and multimodal machine learning. Currently, my projects explore conditional image generation models for applications such as virtual staining and MRI-to-MRI translation, as well as 3D volume registration.

Advisor: Prof. Shireen Elhabian

PhD Commitee Members: Prof. Jeff Phillips, Prof. Ziad Al-Halah, Prof. Tolga Tasdizen, Prof. Beatrice Knudsen

Current Collaborators: Prof. Beatrice S. Knudsen, Mokshagna Sai Teja Karanam, Vivek Gupta, Abu Zahid Bin Aziz, Asma Khan,

Past Collaborators: Shikha Dubey, Krithika Iyer, Jadie Adams, Rachaell Nihalaani, Janmesh Ukey

Reviewer Services Conferences: MICCAI 2024,2025, ARR (June,October) 2024, Feb 2025, ICLR 2025, MIUA 2025

Reviewer Services Journal: Medical Image Analysis 2025, Nature Communication

Internship

• [Aug 2024 -May 2024] Summer Internship at Johnson and Johnson Innovation Labs. During my internship as a Digital Pathology Imaging Intern, I focused on developing methods for TILs detection and contributed to various image processing projects.

Recent News

• [March 2025 -April 2025] Passed My Written PhD Qualifying Exam.

• [April 2025, NAACL 2025] Leveraging LLM For Synchronizing Information Across Multilingual Tables

  Author List: Siddharth Khincha, Tushar Kataria, Ankita Anand, Vivek Gupta, Dan Roth

• [April 2025, NAACL 2025] TransientTables: Evaluating LLMs’ Reasoning on Temporally Evolving Semi-structured Tables

  Author List: Abhilash Shankarampeta, Harsh Mahajan, Tushar Kataria, Vivek Gupta, Dan Roth

• [April 2025, NAACL 2025] NTSEBENCH: Cognitive Reasoning Benchmark for Vision Language Models

  Author List: Pranshu Pandya, Vatsal Gupta, Agney S Talwarr, Tushar Kataria, Vivek Gupta, Dan Roth

• [Feb 2025, WACV-2025] EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registration

  Author List: Abu Zahid Bin Aziz, Mokshagna Sai Teja Karanam,Tushar Kataria,Shireen Elhabian.

Archived Papers

• [Mar 2025, Archive Version] On the Viability of Semi-Supervised Segmentation Methods for Statistical Shape Modeling

  Author List: Asma Khan, Tushar Kataria, Janmesh Ukey, Shireen Y. Elhabian

• [Mar 2024, Archive Version] StainDiffuser: MultiTask Dual Diffusion Model for Virtual Staining

  Author List: Tushar Kataria, Beatrice Knudsen, Shireen Elhabian.

• [May 2025, Archive Version] ImplicitStainer: Data-Efficient Medical Image Translation for Virtual Antibody-based Tissue Staining Using Local Implicit Functions

  Author List: Tushar Kataria, Beatrice Knudsen, Shireen Elhabian.

• [May 2025, Archive Version] BoundarySeg:An Embarrassingly Simple Method To Boost Medical Image Segmentation Performance for Low Data Regimes

  Author List: Tushar Kataria, Shireen Elhabian.

Equal Contribution