Related papers: SpectrumFM: Redefining Spectrum Cognition via Foun…

Semantic communication is a promising technique for emerging wireless applications, which reduces transmission overhead by transmitting only task-relevant features instead of raw data. However, existing methods struggle under extremely low…

Unsupervised semantic segmentation is a long-standing challenge in computer vision with great significance. Spectral clustering is a theoretically grounded solution to it where the spectral embeddings for pixels are computed to construct…

Multimodal time series forecasting is crucial in real-world applications, where decisions depend on both numerical data and contextual signals. The core challenge is to effectively combine temporal numerical patterns with the context…

Small-molecule identification from tandem mass spectrometry (MS/MS) remains a bottleneck in untargeted settings where spectral libraries are incomplete. While deep learning offers a solution, current approaches typically fall into two…

Time series forecasting requires capturing patterns across multiple temporal scales while maintaining computational efficiency. This paper introduces AWGformer, a novel architecture that integrates adaptive wavelet decomposition with…

The joint detection and classification of RF signals has been a critical problem in the field of wideband RF spectrum sensing. Recent advancements in deep learning models have revolutionized this field, remarkably through the application of…

In speech enhancement, complex neural network has shown promising performance due to their effectiveness in processing complex-valued spectrum. Most of the recent speech enhancement approaches mainly focus on wide-band signal with a…

Spectral analysis provides one of the most effective paradigms for information-preserving dimensionality reduction, as simple descriptions of naturally occurring signals are often obtained via few terms of periodic basis functions. In this…

Far-field speech recognition in noisy and reverberant conditions remains a challenging problem despite recent deep learning breakthroughs. This problem is commonly addressed by acquiring a speech signal from multiple microphones and…

We propose the autofocus convolutional layer for semantic segmentation with the objective of enhancing the capabilities of neural networks for multi-scale processing. Autofocus layers adaptively change the size of the effective receptive…

We introduce a framework for designing multi-scale, adaptive, shift-invariant frames and bi-frames for representing signals. The new framework, called AdaFrame, improves over dictionary learning-based techniques in terms of computational…

As the demand for internet of things (IoT) and device-to-device (D2D) applications in next generation communication systems increases, we are confronted with a challenge of spectrum scarcity. One promising solution to this problem is…

Audio-visual speech enhancement system is regarded to be one of promising solutions for isolating and enhancing speech of desired speaker. Conventional methods focus on predicting clean speech spectrum via a naive convolution neural network…

The emergence of large foundation models has propelled significant advances in various domains. The Segment Anything Model (SAM), a leading model for image segmentation, exemplifies these advances, outperforming traditional methods.…

To tackle the prevalence of pseudo changes, the scarcity of labeled samples, and the difficulty of cross-domain generalization in multi-temporal and multi-source remote sensing imagery, we propose PeftCD, a change detection framework built…

In real-world applications with large state and action spaces, reinforcement learning (RL) typically employs function approximations to represent core components like the policies, value functions, and dynamics models. Although powerful…

Speculative decoding has emerged as a promising approach to accelerate autoregressive inference in large language models (LLMs). Self-draft methods, which leverage the base LLM itself for speculation, avoid the overhead of auxiliary draft…

This paper presents a novel approach, Spectral-Interpretable and -Enhanced Transformer (SIEFormer), which leverages spectral analysis to reinterpret the attention mechanism within Vision Transformer (ViT) and enhance feature adaptability,…

As an important part of speech recognition technology, automatic speech keyword recognition has been intensively studied in recent years. Such technology becomes especially pivotal under situations with limited infrastructures and…

Accurate beam prediction is essential for maintaining reliable links and high spectral efficiency in dynamic low-altitude wireless networks. However, existing approaches often fail to capture the deep correlations across heterogeneous…