iiinova — where your digital self keeps evolving

Murat Seçkin Ayhan

@msayhan.bsky.social

Assistant Professor of Computing and Software Systems, UW Bothell Previously UCL and University of Tübingen msayhan.github.io

Posts Replies Media

Murat Seçkin Ayhan @msayhan.bsky.social · 14/07/2026

Seattle, warum bist du so hügelig? 💯💜🫍

000

Murat Seçkin Ayhan @msayhan.bsky.social · 14/01/2026

It’s a beautiful day. 🧿🍀🤞

000

Murat Seçkin Ayhan @msayhan.bsky.social · 10/12/2025

One of the followings, in the order of preference, will be the name of my new GPU server: 1. “turing”: to remember Alan Turing. 2. “heidelberg”: one of the most beautiful cities in Germany. 3. “dartmouth”: for Dartmouth College - the birthplace of AI. What is yours? 😃

100

Murat Seçkin Ayhan @msayhan.bsky.social · 17/09/2025

I have moved to the breathtaking Pacific Northwest and joined the ranks of the University of Washington in Bothell. Here’s to new opportunities, growth, and discovery! 🥂🧿🍀

010

Murat Seçkin Ayhan @msayhan.bsky.social · 08/09/2025

🚨 New paper alert 🚨 Can we match RETFound’s retinal disease detection performance by just prompting a general-purpose foundation model like Gemini 1.5 Pro to the task? For diabetic retinopathy detection from color fundus photos, YES! www.sciencedirect.com/science/arti...

sciencedirect.com

In-context learning for data-efficient diabetic retinopathy detection via multimodal foundation models

This study aims to evaluate whether in-context learning, a prompt-based learning mechanism enabling multimodal foundation models to rapidly adapt to n…

100

Murat Seçkin Ayhan @msayhan.bsky.social · 29/05/2025

I need GPUs, lots of GPUs. 🔥🤓

000

Murat Seçkin Ayhan @msayhan.bsky.social · 22/05/2025

Realistic retinal image generation for counterfactual reasoning in ophthalmology. Diffusion models coupled with robust classifiers led to stunning results. It works on both color fundus photographs and OCT. Finally out in PLOS Digital Health!

lnkd.in

This link will take you to a page that’s not on LinkedIn

000

Murat Seçkin Ayhan @msayhan.bsky.social · 13/03/2025

We matched the performance of RETFound for DR detection from CFPs via in-context learning with Gemini 1.5 Pro. We also achieved counterfactual reasoning about diagnostic decisions in natural language space, plus well-calibrated predictive probabilities.

medrxiv.org

In-context learning for data-efficient classification of diabetic retinopathy with multimodal foundation models

Importance: In-context learning, a prompt-based learning mechanism that enables multimodal foundation models to adapt to new tasks, can eliminate the need for retraining or large annotated datasets. W...

000