Related papers: ARES v2 - new features and improved performance
Error correction techniques remain effective to refine outputs from automatic speech recognition (ASR) models. Existing end-to-end error correction methods based on an encoder-decoder architecture process all tokens in the decoding phase,…
Owing to the edge preserving ability and low computational cost of the total variation (TV), variational models with the TV regularization have been widely investigated in the field of multiplicative noise removal. The key points of the…
Reverberation as supervision (RAS) is a framework that allows for training monaural speech separation models from multi-channel mixtures in an unsupervised manner. In RAS, models are trained so that sources predicted from a mixture at an…
Real-time estimation of vehicle-tire-road friction is critical for allowing autonomous race cars to safely and effectively operate at their physical limits. Traditional approaches to measure tire grip often depend on costly, specialized…
In recent years, a number of new instruments and data reduction pipelines have been developed to obtain high-precision radial velocities (RVs). In particular in the optical, considerable progress has been made and RV precision below 50 cm/s…
Most sensor setups for onboard autonomous perception are composed of LiDARs and vision systems, as they provide complementary information that improves the reliability of the different algorithms necessary to obtain a robust scene…
This paper discusses the overall quality of IUE high resolution data processed with the NEWSIPS software in terms of flux and wavelength accuracy. It also describes the processing of NEWSIPS high resolution spectra within the framework of…
Rubric-based reward shaping provides interpretable and editable reward signals for fine-tuning LLMs via reinforcement learning (RL), but existing adaptive rubric methods typically update criteria from local evidence such as the current…
Rubric-based rewards offer a promising way to extend reinforcement learning (RL) for large language models beyond tasks with automatically verifiable answers. However, scaling rubric-based RL remains challenging: existing approaches often…
We explore the radial velocity performance benefits of coupling starlight to a fast-scanning interferometer and a fast-readout spectrometer with zero readout noise. By rapidly scanning an interferometer we can decouple wavelength…
In this article, we establish a class of new accelerated modulus-based iteration methods for solving the linear complementarity problem. When the system matrix is an $H_+$-matrix, we present appropriate criteria for the convergence…
The integration of artificial intelligence (AI) into medical diagnostic workflows requires robust and consistent evaluation methods to ensure reliability, clinical relevance, and the inherent variability in expert judgments. Traditional…
Processing Using Memory (PUM) accelerators have the potential to perform Deep Neural Network (DNN) inference by using arrays of memory cells as computation engines. Among various memory technologies, ReRAM crossbars show promising…
Existing supervised action segmentation methods depend on the quality of frame-wise classification using attention mechanisms or temporal convolutions to capture temporal dependencies. Even boundary detection-based methods primarily depend…
Information retrieval (IR) methods, like retrieval augmented generation, are fundamental to modern applications but often lack statistical guarantees. Conformal prediction addresses this by retrieving sets guaranteed to include relevant…
This letter presents an adaptive spectrum sensing algorithm that detects wideband spectrum using sub-Nyquist sampling rates. By taking advantage of compressed sensing (CS), the proposed algorithm reconstructs the wideband spectrum from…
Automated Essay Scoring (AES) plays a crucial role in education by providing scalable and efficient assessment tools. However, in real-world settings, the extreme scarcity of labeled data severely limits the development and practical…
Abstract Meaning Representation (AMR) parsing has experienced a notable growth in performance in the last two years, due both to the impact of transfer learning and the development of novel architectures specific to AMR. At the same time,…
ASR Error Detection (AED) models aim to post-process the output of Automatic Speech Recognition (ASR) systems, in order to detect transcription errors. Modern approaches usually use text-based input, comprised solely of the ASR…
Given 2D point correspondences between an image pair, inferring the camera motion is a fundamental issue in the computer vision community. The existing works generally set out from the epipolar constraint and estimate the essential matrix,…