Zobrazeno 1 - 10
of 26 422
pro vyhledávání: '"A. Ferhat"'
In recent years, vision-language models (VLMs) have been applied to various fields, including healthcare, education, finance, and manufacturing, with remarkable performance. However, concerns remain regarding VLMs' consistency and uncertainty, partic
Externí odkaz:
http://arxiv.org/abs/2412.00056
Autor:
Bertalis, Nerijus, Granse, Paul, Gül, Ferhat, Hauss, Florian, Menkel, Leon, Schüler, David, Speier, Tom, Galke, Lukas, Scherp, Ansgar
Assigning a subset of labels from a fixed pool of labels to a given input text is a text classification problem with many real-world applications, such as in recommender systems. Two separate research streams address this issue. Hierarchical Text Cla
Externí odkaz:
http://arxiv.org/abs/2411.13687
Autor:
Zeiltinger, Julia, Roy, Sushmita, Ay, Ferhat, Mathelier, Anthony, Medina-Rivera, Alejandra, Mahony, Shaun, Sinha, Saurabh, Ernst, Jason
Predicting how genetic variation affects phenotypic outcomes at the organismal, cellular, and molecular levels requires deciphering the cis-regulatory code, the sequence rules by which non-coding regions regulate genes. In this perspective, we discus
Externí odkaz:
http://arxiv.org/abs/2411.04363
Autor:
Miner, Stephen, Takashima, Yoshiki, Han, Simeng, Erata, Ferhat, Antonopoulos, Timos, Piskac, Ruzica, Shapiro, Scott J
Benchmarks are critical for measuring progress of math reasoning abilities of Large Language Models (LLMs). However, existing widely-used benchmarks such as GSM8K have been rendered less useful as multiple cutting-edge LLMs achieve over 94% accuracy.
Externí odkaz:
http://arxiv.org/abs/2410.00151
Autor:
Zoellin, Jay, Merk, Colin, Buob, Mischa, Saad, Amr, Giesser, Samuel, Spitznagel, Tahm, Turgut, Ferhat, Santos, Rui, Zhou, Yukun, Wagner, Sigfried, Keane, Pearse A., Tham, Yih Chung, DeBuc, Delia Cabrera, Becker, Matthias D., Somfai, Gabor M.
Integrating deep learning into medical imaging is poised to greatly advance diagnostic methods but it faces challenges with generalizability. Foundation models, based on self-supervised learning, address these issues and improve data efficiency. Natu
Externí odkaz:
http://arxiv.org/abs/2409.17332
In recent years, neural networks have been used to implement symmetric cryptographic functions for secure communications. Extending this domain, the proposed approach explores the application of asymmetric cryptography within a neural network framewo
Externí odkaz:
http://arxiv.org/abs/2407.08831
Autor:
Catak, Ferhat Ozgur, Kuzlu, Murat
Uncertainty quantification approaches have been more critical in large language models (LLMs), particularly high-risk applications requiring reliable outputs. However, traditional methods for uncertainty quantification, such as probabilistic models a
Externí odkaz:
http://arxiv.org/abs/2406.19712
Autor:
Erata, Ferhat, Chiu, TingHung, Etim, Anthony, Nampally, Srilalith, Raju, Tejas, Ramu, Rajashree, Piskac, Ruzica, Antonopoulos, Timos, Xiong, Wenjie, Szefer, Jakub
This work presents a novel, black-box software-based countermeasure against physical attacks including power side-channel and fault-injection attacks. The approach uses the concept of random self-reducibility and self-correctness to add randomness an
Externí odkaz:
http://arxiv.org/abs/2405.05193
Fault Detection and Monitoring using an Information-Driven Strategy: Method, Theory, and Application
The ability to detect when a system undergoes an incipient fault is of paramount importance in preventing a critical failure. In this work, we propose an information-driven fault detection method based on a novel concept drift detector. The method is
Externí odkaz:
http://arxiv.org/abs/2405.03667
Autor:
DEMİRTAŞ, TUNÇ, PİRİNÇÇİ, FERHAT
Publikováno v:
Insight Turkey, 2024 Jul 01. 26(3), 103-130.
Externí odkaz:
https://www.jstor.org/stable/48790774
