Berk Tınaz

Hi there! I am a 4th year PhD student in Electrical and Computer Engineering at University of Southern California (USC). I'm fortunate to be advised by Prof. Mahdi Soltanolkotabi at the USC Center on AI Foundations for Science (AIF4S).

Previously, I was an undergraduate student in the Department of Electrical and Electronics Engineering at Bilkent University, where I worked in Imaging and Computational Neuroscience Laboratory (ICON Lab) in National Magnetic Resonance Research Center under the supervision of Prof. Tolga Çukur with a focus on deep learning for accelerated MRI synthesis and reconstruction.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github  /  Linkedin

profile photo
News
  • (Jan 2024) Will be joining Amazon as an Applied Science Intern for the summer of 2024!
  • (Dec 2022) Completed my M.Sc. degree!
  • (Apr 2022) Will be attending Princeton ML Theory Summer School organized by Boris Hanin this June. Excited to visit beautiful campus of Princeton University and IAS!
  • (Dec 2021) Passed SIPI screening exam!
  • (May 2021) Will be attending CIFAR's Deep Learning + Reinforcement Learning (DLRL) and MLSS summer schools.
  • (Apr 2020) Website is live! Received offers from UCLA, USC, and UBC. Very excited to join USC for my PhD studies next fall.
Research

My current research direction aims to analyze convergence of shallow neural networks with small initialization as well as developing algorithms for inverse problems (such as denoising, deblurring, MRI reconstruction, etc.). Recently, I am also interested with reasoning in large language models (LLMs), particularly the ability to do self-feedback and which tasks actually benefit from it. Selected papers are shown below.

Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models
Berk Tinaz*, Zalan Fabian*, Mahdi Soltanolkotabi,
arXiv, 2023
NeurIPS Deep Inverse Workshop, 2023
GitHub / Paper Link

Latent diffusion based reconstruction of degraded images by estimating the severity of degradation and initiating the reverse diffusion sampling accordingly to achieve sample-adaptive inference times.

DiracDiffusion: Denoising and Incremental Reconstruction with Assured Data-Consistency
Zalan Fabian, Berk Tinaz, Mahdi Soltanolkotabi,
arXiv, 2023
GitHub / Paper Link

Novel framework for solving inverse problems that maintains consistency with the original measurement throughout the reverse process and allows for great flexibility in trading off perceptual quality for improved distortion metrics and sampling speedup via early-stopping.

HUMUS-Net: Hybrid Unrolled Multi-scale Network Architecture for Accelerated MRI Reconstruction
Zalan Fabian, Berk Tinaz, Mahdi Soltanolkotabi,
NeurIPS, 2022
GitHub / Paper Link

A hybrid architecture that combines the implicit bias and efficiency of conbolutions with the power of Transformer blocks in an unrolled and multi-scale network to establish SOTA on fastMRI dataset.


Website template is proudly stolen from Jon Barron (source code).