Vision and Immersive Realities Lab CS@UTSA

Email:
ofmriazrahman.aranya@utsa.edu

Office:
SP1 Room: 340J, 506 Dolorosa St, San Antonio, TX 78204

CV:
Preview | Download

Links:

About Me

I’m currently a doctoral student in Computer Science at the University of Texas at San Antonio (UTSA). Before starting my Ph.D., I worked as a software engineer at several software companies based in Dhaka, Bangladesh, where I gained hands-on experience in full-stack development and real-world software engineering.

I work on medical image analysis and vision-language models. Some of my work is on the images themselves: segmentation and reconstruction. The rest is on models that look at two scans of the same patient taken at different times and describe what changed and where. I also work on making these models more reliable. I test how they respond when a user tells them they are wrong, and I measure how small a change a scan can actually show, so a model can tell a real change from noise.

Research Interests

  • Medical Vision language model
  • Image segmentation
  • Image reconstruction
  • Generative AI
  • Synthetic data

Work Experience

  • Graduate Research Assistant, UTSA (Jan 2026 - Present)
  • Graduate Teaching Assistant, UTSA (Aug 2023 - Dec 2025)
  • Software Engineer, RedDot Digital Ltd (Mar 2023 - Jul 2023)
  • Jr. Software Engineer, Nascenia Ltd (Dec 2020 - Feb 2023)

Education

  • Ph.D. in Computer Science, UT San Antonio (Expected graduate: 2028)
  • BSc in Computer Science and Engineering, Khulna University of Engineering & Technology, 2020

Awards

  • Best Paper Award, Med-Reasoner workshop, CVPR 2026
  • 1st Runner UP, LICT Project Showcasing Jashore IT park, 2019

Recent Publications

Toward Faithful Segmentation Attribution via Benchmarking and Dual-Evidence Fusion
Toward Faithful Segmentation Attribution via Benchmarking and Dual-Evidence Fusion
Abu Noman Md Sakib, OFM Riaz Rahman Aranya, Kevin Desai, Zijie Zhang
CVPR 2026 Workshop (HOW)  ·  23 Mar 2026  ·  DOI: https://doi.org/10.48550/arXiv.2603.22624
To Agree or To Be Right The Grounding-Sycophancy Tradeoff in Medical Vision-Language Models
To Agree or To Be Right? The Grounding-Sycophancy Tradeoff in Medical Vision-Language Models
OFM Riaz Rahman Aranya, Kevin Desai
CVPR 2026 Workshop (Med-Reasoner)  ·  23 Mar 2026  ·  DOI: https://doi.org/10.48550/arXiv.2603.22623
TRACE: Temporal Radiology with Anatomical Change Explanation for Grounded X-ray Report Generation
TRACE: Temporal Radiology with Anatomical Change Explanation for Grounded X-ray Report Generation
OFM Riaz Rahman Aranya, Kevin Desai
ICPR 2026  ·  05 Feb 2026  ·  DOI: https://doi.org/10.48550/arXiv.2602.02963

See all publications