Research Project: Exact dynamics of online and distributed learning algorithms for large-scale non-convex optimization problems
Loading...
Contributors
Funders
ID
TB.00479
Authors
Doğan, Zafer
Faculty Member
Publications
Leveraging vision-language models to select trustworthy super-resolution samples generated by diffusion models
(IEEE, 2026) Korkmaz, Cansu; Tekalp, Ahmet Murat; Doğan, Zafer; Korkmaz, Cansu; Department of Electrical and Electronics Engineering; KUIS AI (Koç University & İş Bank Artificial Intelligence Center); Yes; College of Engineering; Research Center
Super-resolution (SR) is an ill-posed inverse problem with many feasible solutions consistent with a given low-resolution image. On one hand, regressive SR models aim to balance fidelity and perceptual quality to yield a single solution, but this trade-off often introduces artifacts that create ambiguity in information-critical applications such as recognizing digits or letters. On the other hand, diffusion models generate a diverse set of SR images, but selecting the most trustworthy solution from this set remains a challenge. This paper introduces a robust, automated framework for identifying the most trustworthy SR sample from a diffusion-generated set by leveraging the semantic reasoning capabilities of vision-language models (VLMs). Specifically, VLMs such as BLIP-2, GPT-4o, and their variants are prompted with structured queries to assess semantic correctness, visual quality, and artifact presence. The top-ranked SR candidates are then ensembled to yield a single trustworthy output in a cost-effective manner. To rigorously assess the validity of VLM-selected samples, we propose a novel Trustworthiness Score (TWS) a hybrid metric that quantifies SR reliability based on three complementary components: semantic similarity via CLIP embeddings, structural integrity using SSIM on edge maps, and artifact sensitivity through multi-level wavelet decomposition. We empirically show that TWS correlates strongly with human preference in both ambiguous and natural images, and that VLM-guided selections consistently yield high TWS values. Compared to conventional metrics like PSNR, LPIPS, which fail to reflect information fidelity, our approach offers a principled, scalable, and generalizable solution for navigating the uncertainty of the diffusion SR space. By aligning outputs with human expectations and semantic correctness, this work sets a new benchmark for trustworthiness in generative SR.
Machine learning-enabled multiplexed microfluidic sensors
(American Institute of Physics (AIP) Publishing, 2020) Dabbagh, Sajjad Rahmani; Doğan, Zafer; Rabbi, Fazle; Taşoğlu, Savaş; Yetişen, Ali Kemal; Department of Electrical and Electronics Engineering; Department of Mechanical Engineering; Graduate School of Sciences and Engineering; Graduate School of Social Sciences and Humanities; KUAR (KU Arçelik Research Center for Creative Industries); KUTTAM (Koç University Research Center for Translational Medicine); Yes; College of Engineering; GRADUATE SCHOOL OF SCIENCES AND ENGINEERING; GRADUATE SCHOOL OF SOCIAL SCIENCES AND HUMANITIES; Research Center
High-throughput, cost-effective, and portable devices can enhance the performance of point-of-care tests. Such devices are able to acquire images from samples at a high rate in combination with microfluidic chips in point-of-care applications. However, interpreting and analyzing the large amount of acquired data is not only a labor-intensive and time-consuming process, but also prone to the bias of the user and low accuracy. Integrating machine learning (ML) with the image acquisition capability of smartphones as well as increasing computing power could address the need for high-throughput, accurate, and automatized detection, data processing, and quantification of results. Here, ML-supported diagnostic technologies are presented. These technologies include quantification of colorimetric tests, classification of biological samples (cells and sperms), soft sensors, assay type detection, and recognition of the fluid properties. Challenges regarding the implementation of ML methods, including the required number of data points, image acquisition prerequisites, and execution of data-limited experiments are also discussed.
