arXiv subjects

Ceyhun Efe Kayan

Publications and source records attributed to Ceyhun Efe Kayan.

5 recordsLinked to original sources

arXiv2026

A Reality Check of Language Models as Formalizers on Constraint Satisfaction Problems

Recent work shows superior performance when using large language models (LLMs) as formalizers instead of as end-to-end solvers for symbolic reasoning problems. Given the problem description, the LLM generates a formal program that derives a solution via an external solver. We systematically investigate the formalization capability of LLMs on real-life constraint satisfaction problems on 4 benchmarks, 6 LLMs, and 2 types of formal languages. We show that LLM-as-formalizer by no means trivializes the problem but underperforms LLM-as-solver in 15 out of 24 model-dataset combinations, despite the former's verifiability and interpretability. Although the formalization space is magnitudes smaller than the search space, our scaling analysis shows that LLM-as-formalizer still drastically degrades as problem complexity increases similar to LLM-as-solver. To better understand this limitation, we observe excessive, solver-like reasoning tokens that sometimes lead to hard-coded solutions, highlighting a key challenge for improving LLM-based formalization.

cs.CL↗

arXiv2025

Prototype-Based Dynamic Steering for Large Language Models

Despite impressive breadth, LLMs still rely on explicit reasoning instructions or static, one-fits-all steering methods, leaving a gap for adaptive, instruction-free reasoning amplification. We present Prototype-Based Dynamic Steering (PDS), a test-time method that amplifies large language model (LLM) reasoning without adding or altering instructions. We introduce "reasoning prototypes" by clustering activation differences between Chain-of-Thought (CoT) and neutral prompts. At inference, an input's hidden state is projected onto these prototypes to form an instance-specific steering vector. Evaluated on GSM8K, AQuA-RAT, and BIG-Bench tasks, PDS consistently improves accuracy without fine-tuning or prompt engineering. Notably, the gains persist even when CoT is explicitly suppressed to improve cost-efficiency, indicating that the intervention strengthens latent reasoning processes rather than inducing a superficial behavioral shift. These results position dynamic, prototype-guided steering as a lightweight alternative to training-time approaches for enhancing LLM reasoning.

cs.CL↗

arXiv2025

GPU-Accelerated Simulated Oscillator Ising/Potts Machine Solving Combinatorial Optimization Problems

Oscillator-based Ising machines (OIMs) and oscillator-based Potts machines (OPMs) have emerged as promising hardware accelerators for solving NP-hard combinatorial optimization problems by leveraging the phase dynamics of coupled oscillators. In this work, a GPU-accelerated simulated OIM/OPM digital computation framework capable of solving combinatorial optimization problems is presented. The proposed implementation harnesses the parallel processing capabilities of GPUs to simulate large-scale OIM/OPMs, leveraging the advantages of digital computing to offer high precision, programmability, and scalability. The performance of the proposed GPU framework is evaluated on the max-cut problems from the GSET benchmark dataset and graph coloring problems from the SATLIB benchmarks dataset, demonstrating competitive speed and accuracy in tackling large-scale problems. The results from simulations, reaching up to 11295x speed-up over CPUs with up to 99% accuracy, establish this framework as a scalable, massively parallelized, and high-fidelity digital realization of OIM/OPMs.

cs.AR↗

arXiv2023

Deep reproductive feature generation framework for the diagnosis of COVID-19 and viral pneumonia using chest X-ray images

The rapid and accurate detection of COVID-19 cases is critical for timely treatment and preventing the spread of the disease. In this study, a two-stage feature extraction framework using eight state-of-the-art pre-trained deep Convolutional Neural Networks (CNNs) and an autoencoder is proposed to determine the health conditions of patients (COVID-19, Normal, Viral Pneumonia) based on chest X-rays. The X-ray scans are divided into four equally sized sections and analyzed by deep pre-trained CNNs. Subsequently, an autoencoder with three hidden layers is trained to extract reproductive features from the concatenated ouput of CNNs. To evaluate the performance of the proposed framework, three different classifiers, which are single-layer perceptron (SLP), multi-layer perceptron (MLP), and support vector machine (SVM) are used. Furthermore, the deep CNN architectures are used to create benchmark models and trained on the same dataset for comparision. The proposed framework outperforms other frameworks wih pre-trained feature extractors in binary classification and shows competitive results in three-class classification. The proposed methodology is task-independent and suitable for addressing various problems. The results show that the discriminative features are a subset of the reproductive features, suggesting that extracting task-independent features is superior to the extraction only task-based features. The flexibility and task-independence of the reproductive features make the conceptive information approach more favorable. The proposed methodology is novel and shows promising results for analyzing medical image data.

eess.IV↗

arXiv2022

An Intensity and Phase Stacked Analysis of Phase-OTDR System using Deep Transfer Learning and Recurrent Neural Networks

Distributed acoustic sensors (DAS) are effective apparatus which are widely used in many application areas for recording signals of various events with very high spatial resolution along the optical fiber. To detect and recognize the recorded events properly, advanced signal processing algorithms with high computational demands are crucial. Convolutional neural networks are highly capable tools for extracting spatial information and very suitable for event recognition applications in DAS. Long-short term memory (LSTM) is an effective instrument for processing sequential data. In this study, we proposed a multi-input multi-output, two stage feature extraction methodology that combines the capabilities of these neural network architectures with transfer learning to classify vibrations applied to an optical fiber by a piezo transducer. First, we extracted the differential amplitude and phase information from the Phase-OTDR recordings and stored them in a temporal-spatial data matrix. Then, we used a state-of-the-art pre-trained CNN without dense layers as a feature extractor in the first stage. In the second stage, we used LSTMs to further analyze the features extracted by the CNN. Finally, we used a dense layer to classify the extracted features. To observe the effect of the utilized CNN architecture, we tested our model with five state-of-the art pre-trained models (VGG-16, ResNet-50, DenseNet-121, MobileNet and Inception-v3). The results show that using the VGG-16 architecture in our framework manages to obtain 100% classification accuracy in 50 trainings and got the best results on our Phase-OTDR dataset. Outcomes of this study indicate that the pre-trained CNNs combined with LSTM are very suitable for the analysis of differential amplitude and phase information, represented in a temporal spatial data matrix which is promising for event recognition operations in DAS applications.

cs.LG↗