Related papers: ARES v2 - new features and improved performance

Large Reasoning Language Models (LRLMs or LRMs) demonstrate remarkable capabilities in complex reasoning tasks, but suffer from significant computational inefficiencies due to overthinking phenomena. Existing efficient reasoning methods…

We propose two new methods to address the weak scaling problems of KRR: the Balanced KRR (BKRR) and K-means KRR (KKRR). These methods consider alternative ways to partition the input dataset into p different parts, generating p different…

Absolute rotation estimation is an important topic in 3D computer vision. Existing works in literature generally employ a multi-stage (at least two-stage) estimation strategy where multiple independent operations (feature matching, two-view…

A novel framework to enhance the angular resolution of automotive radars is proposed. An approach to enlarge the antenna aperture using artificial neural networks is developed using a self-supervised learning scheme. Data from a high…

Radars and cameras are mature, cost-effective, and robust sensors and have been widely used in the perception stack of mass-produced autonomous driving systems. Due to their complementary properties, outputs from radar detection (radar…

Consistency regularization (CR) improves the robustness and accuracy of Connectionist Temporal Classification (CTC) by ensuring predictions remain stable across input perturbations. In this work, we propose Align-Consistency, an extension…

This paper analyzes monostatic sensing by a user equipment (UE) for a setting in which the UE is unable to resolve multiple targets due to their interference within a single resolution bin. It is shown how sensing accuracy, in terms of both…

Based on continuously recorded beam positions and corrector excitations from, for example, a closed-orbit feedback system we describe an algorithm that continuously updates an estimate of the orbit response matrix. The speed of convergence…

Writing concurrent programs is highly error-prone due to the nondeterminism in interprocess communication. The most reliable indicators of errors in concurrency are data races, which are accesses to a shared resource that can be executed…

Audio pattern recognition (APR) is an important research topic and can be applied to several fields related to our lives. Therefore, accurate and efficient APR systems need to be developed as they are useful in real applications. In this…

Regular expression matching is essential for many applications, such as finding patterns in text, exploring substrings in large DNA sequences, or lexical analysis. However, sequential regular expression matching may be time-prohibitive for…

There is significant scientific value to be gained from combining AKARI fluxes with data at other far-IR wavelengths from the IRAS and Herschel missions. To be able to do this we must ensure that there are no systematic differences between…

Stereo matching is a critical task for robot navigation and autonomous vehicles, providing the depth estimation of surroundings. Among all stereo matching algorithms, Efficient Large-scale Stereo (ELAS) offers one of the best tradeoffs…

Lane detection is an integral part of control systems in autonomous vehicles and lane departure warning systems as lanes are a key component of the operating environment for road vehicles. In a previous paper, a robust neural network output…

We present a stationary iteration method, namely Alternating Symmetric positive definite and Scaled symmetric positive semidefinite Splitting (ASSS), for solving the system of linear equations obtained by using finite element discretization…

We present a review of high-performance automatic modulation recognition (AMR) models proposed in the literature to classify various Radio Frequency (RF) modulation schemes. We replicated these models and compared their performance in terms…

State-of-the-art end-to-end automatic speech recognition (ASR) extracts acoustic features from input speech signal every 10 ms which corresponds to a frame rate of 100 frames/second. In this report, we investigate the use of high-frame-rate…

In recent years, end to end steering prediction for autonomous vehicles has become a major area of research. The primary method for achieving end to end steering was to use computer vision models on a live feed of video data. However, to…

Fluid reconfigurable intelligent surfaces (FRIS) extend conventional RIS architectures by enabling physical reconfiguration of element positions, thereby introducing a fundamentally new degree of freedom for controlling spatial correlation…

This paper describes methods for evaluating automatic speech recognition (ASR) systems in comparison with human perception results, using measures derived from linguistic distinctive features. Error patterns in terms of manner, place and…