Mehmet Yigit Turali

Engineering IV Building

UCLA

Los Angeles, CA 90095

I’m a M.S./Ph.D. student at the Department of Electrical and Computer Engineering, University of California, Los Angeles, advised by Prof. Vwani P. Roychowdhury. My research sits at the intersection of large language models, structured memory, and machine learning for healthcare.

Currently, I’m building non-parametric continual-learning systems that encode documents into entity- and event-aware structured memories — Generative Semantic Workspaces (GSW) — and reason over them via inference-chain retrieval. This work led to PANINI (ICML 2026), which delivers competitive multi-hop QA accuracy with 2–30× fewer answer-context tokens than baselines.

In Summer 2026, I will serve as the Academic Mentor for the OpenAI team at the IPAM RIPS program at UCLA — partnering with OpenAI to advise a team of top undergraduates on an OpenAI-sponsored summer research project.

I also work on:

NLP for genomics: reference-free DNA embeddings and one-shot structural-variant detection treating DNA as a specialized language.
Brain-organoid computing: reservoir-computing approaches that harness biological neural networks for chaotic time-series forecasting.
GlobalHealthLLM: LLM-driven standardization of pediatric epilepsy records from rural Ugandan clinics, supporting medication-decision tools.

Before UCLA, I earned my B.S. in Electrical and Electronics Engineering at Bilkent University (Summa Cum Laude, 2024), where I was a researcher under Prof. S. Serdar Kozat publishing on adaptive feature selection, gradient-boosted sequential regression, and SGD-based filtering. I’m a recipient of the Bilkent Research Excellence Award (2024) and the Responsible AI Innovation Award (MathWorks / FIGES / Tubitak Sage, 2024).

Feel free to reach out if you’d like to chat about LLM memory systems, ML for health, or computational neuroscience.

news

May 04, 2026	🤝 Thrilled to share that I’ll be the Academic Mentor for the OpenAI team this summer at the IPAM RIPS program at UCLA (June 22 – August 21, 2026) — partnering with OpenAI to mentor a team of top undergraduates on an OpenAI-sponsored research project.
Apr 25, 2026	🎉 Our recent paper PANINI: Continual Learning in Token Space via Structured Memory has been accepted to ICML 2026 (poster)! Joint work with S. Rajesh, P. S. Holur, C. Duan, and Prof. V. Roychowdhury.
Mar 25, 2026	📚 TA’ing M146: Introduction to Machine Learning at UCLA this Spring 2026 quarter.
Jan 06, 2026	📚 TA’ing ECE C147: Neural Networks and Deep Learning at UCLA in Winter 2026.
Oct 20, 2025	🎉 Our demo paper on customizing open-source LLMs for medication-attribute extraction across heterogeneous EHR systems has been accepted to the NeurIPS 2025 Workshop on GenAI for Health: Potential, Trust, and Policy Compliance!

selected publications

ICML
Panini: Continual Learning in Token Space via Structured Memory

S. Rajesh, P. S. Holur, M. Y. Turali, and 2 more authors

In Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026

Accepted as poster. *Equal contribution by Rajesh and Holur.

Abs Bib

PANINI is a non-parametric continual-learning framework that encodes documents into Generative Semantic Workspaces (GSW)—entity- and event-aware networks of atomic question-answer pairs. A beam-search retrieval procedure (Reasoning Inference Chain Retrieval, RICR) follows multi-hop inference chains through GSWs to assemble compact evidence, achieving top average performance across six QA benchmarks while using 2-30x fewer answer-context tokens than competitive baselines.
@inproceedings{rajesh2026panini, title = {Panini: Continual Learning in Token Space via Structured Memory}, author = {Rajesh, S. and Holur, P. S. and Turali, M. Y. and Duan, C. and Roychowdhury, V.}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning (ICML)}, year = {2026}, note = {Accepted as poster. *Equal contribution by Rajesh and Holur.} }
NeurIPS-W
Demo: Customizing Open-Source LLMs for Quantitative Medication Attribute Extraction across Heterogeneous EHR Systems

Z. Fei, M. Y. Turali, S. Rajesh, and 7 more authors

In NeurIPS 2025 Workshop on GenAI for Health: Potential, Trust, and Policy Compliance, 2025

Accepted as poster. *Equal contribution by Fei and Turali.

Abs Bib

We customize open-source LLMs to extract quantitative medication attributes (dose, frequency, duration) from heterogeneous electronic health record systems, demonstrating robustness across formats relevant to addiction-medicine deployments.
@inproceedings{fei2025ehrllm, title = {Demo: Customizing Open-Source LLMs for Quantitative Medication Attribute Extraction across Heterogeneous EHR Systems}, author = {Fei, Z. and Turali, M. Y. and Rajesh, S. and Dai, X. and Pham, H. and Holur, P. S. and Zhu, Y. and Mooney, L. J. and Hser, Y.-I. and Roychowdhury, V.}, booktitle = {NeurIPS 2025 Workshop on GenAI for Health: Potential, Trust, and Policy Compliance}, year = {2025}, note = {Accepted as poster. *Equal contribution by Fei and Turali.} }