All researchers should fight against this. Every week I try to persuade my students that top papers often have few quantitative results. With work that's new, important, and clearly qualitatively different (zero to one!), you don't need quantitative results. Demos not tables!

In this work, we show that fine-tuning LLMs on synthetic/generated data isn’t the privacy silver bullet it might seem. In fact, it can amplify privacy risks — making models even more vulnerable to membership inference and PII leakage attacks.

It was a joint work with Atilla Akkus, Masoud, Mingjie Li, Junjie Chu, Michael Backes, Yang Zhang. We are excited to present this work in Seattle — hope to see many of you there! ✈️📍

Yann LeCun is not so optimistic about LLMs. 😟 "We are not going to get to human level AI by just scaling up MLMs. This is just not going to happen. There's no way. Okay, absolutely no way. And whatever you can hear from some of my uh more adventurous colleagues, it's not going

See our new paper with Sinem Sav and Kousar Saleem about a new vulnerability of the genomic data sharing beacon protocol in Bioinformatics👇

UTRGAN: Learning to Generate 5’ UTR Sequences for Optimized Translation Efficiency and Gene Expression. #5UTRs #TranslationalControl #TranslationOptimization #GeneExpression #Genomics #Bioinformatics Bioinformatics Advances academic.oup.com/bioinformatics…

📢📢Our study on designing novel 5’ UTRs to that yield higher expression levels and mean ribosome load for the target genes is now published in Bioinformatics Advances. This was a study with graduates from my group Sina Barazandeh, furkan ozden; and a collaboration with Urartu Şeker and his student

Enjoying the ocean view CGSI-The Computational Genomics Summer Institute 2025 with Ahmet Arda Ceylan from our group 📸

Team Bilkent CGSI-The Computational Genomics Summer Institute

'About your cat, Mr. Schrödinger — I have good news and bad news.' (Benjamin Schwartz, New Yorker)

🛫 CGSI-The Computational Genomics Summer Institute is in the books. The best meeting ever.

It is a wrap. #ISMBECCB2025 was a nice mix of jetlag, catching up with friends, observing the state-of-the-art and presenting. It is time to go back home after a loong journey (Izmir - Ayvalık - Los Angeles - London - Liverpool). See ya, mate!

#RECOMB2026 will be in Thessaloniki, Greece on May 26-29, 2026. Satellites on May 24-25. Save the date! Το συνέδριο #RECOMB2026 θα πραγματοποιηθεί στη Θεσσαλονίκη, στις 26-29 Μαΐου 2026. Οι δορυφορικές εκδηλώσεις θα διεξαχθούν στις 24-25 Μαΐου 2026. Σημειώστε την ημερομηνία!

Very happy to announce that our study on designing RNA to bind and target proteins is now published PLOS Comp Biol. RNAtranslator is a generative language model that formulates protein-conditional RNA design as a sequence-to-sequence natural language translation problem for the