Related papers: SAMA-IR: comprehensive input refinement methodolog…
A robust summarization system should be able to capture the gist of the document, regardless of the specific word choices or noise in the input. In this work, we first explore the summarization models' robustness against perturbations…
Magnetic Resonance Imaging (MRI) field-strength enhancement holds immense value for both clinical diagnostics and advanced research. However, existing methods typically focus on isolated enhancement tasks, such as specific 64mT-to-3T or…
Automatic Mean Opinion Score (MOS) prediction is crucial to evaluate the perceptual quality of the synthetic speech. While recent approaches using pre-trained self-supervised learning (SSL) models have shown promising results, they only…
The paper proposes an efficient, robust, and reconfigurable technique to suppress various types of noises for any sampling rate. The theoretical analyses, subjective and objective test results show that the proposed noise suppression (NS)…
Nonnegative matrix factorization (NMF) has been widely used to dimensionality reduction in machine learning. However, the traditional NMF does not properly handle outliers, so that it is sensitive to noise. In order to improve the…
Speech enhancement (SE) methods mainly focus on recovering clean speech from noisy input. In real-world speech communication, however, noises often exist in not only speaker but also listener environments. Although SE methods can suppress…
Recent advancements in Large Language Models (LLMs) have set themselves apart with their exceptional performance in complex language modelling tasks. However, these models are also known for their significant computational and storage…
This paper investigates beam training for extremely large-scale multiple-input multiple-output systems. By considering both the near field and far field, a triple-refined hybrid-field beam training scheme is proposed, where high-accuracy…
Quantum error correction can reduce the effects of noise in quantum systems, e.g. in metrology or most notably in quantum computing. Typically, this requires making measurements that provide information about the errors that have occurred…
We consider a cooperative non-orthogonal multiple access system with radio frequency energy harvesting, in which a user with good channel harvests energy from its received signal and serves as a decode-and-forward relay for enhancing the…
Sharpness-Aware Minimization (SAM) enhances generalization by reducing a Max-Sharpness (MaxS). Despite the practical success, we empirically found that the MAxS behind SAM's generalization enhancements face the "Flatness Indicator Problem"…
The amplification obtained using weak values is quantified through a detailed investigation of the signal to noise ratio for an optical beam deflection measurement. We show that for a given deflection, input power and beam radius, the use…
Parameter Efficient Fine-Tuning (PEFT) methods have gained popularity and democratized the usage of Large Language Models (LLMs). Recent studies have shown that a small subset of weights significantly impacts performance. Based on this…
Image quality assessment (IQA) focuses on the perceptual visual quality of images, playing a crucial role in downstream tasks such as image reconstruction, compression, and generation. The rapid advancement of multi-modal large language…
We describe the validation of the HERA Phase I software pipeline by a series of modular tests, building up to an end-to-end simulation. The philosophy of this approach is to validate the software and algorithms used in the Phase I upper…
In this paper we describe the recent advancements made in the IBM i-vector speaker recognition system for conversational speech. In particular, we identify key techniques that contribute to significant improvements in performance of our…
Reasoning over ultra-long documents requires synthesizing sparse evidence scattered across distant segments under strict memory constraints. While streaming agents enable scalable processing, their passive memory update strategy often fails…
Recent studies on deep neural networks show that flat minima of the loss landscape correlate with improved generalization. Sharpness-aware minimization (SAM) efficiently finds flat regions by updating the parameters according to the…
Non-intrusive load monitoring (NILM) is an advanced load monitoring technique that uses data-driven algorithms to disaggregate the total power consumption of a household into the consumption of individual appliances. However, real-world…
Composed image retrieval (CIR) is a vision language task that retrieves a target image using a reference image and modification text, enabling intuitive specification of desired changes. While effectively fusing visual and textual…