Related papers: ECHO: Frequency-aware Hierarchical Encoding for Va…

Biological multimodal large language models (MLLMs) have emerged as powerful foundation models for scientific discovery. However, existing models are specialized to a single modality, limiting their ability to solve inherently cross-modal…

In daily life, graphic symbols, such as traffic signs and brand logos, are ubiquitously utilized around us due to its intuitive expression beyond language boundary. We tackle an open-set graphic symbol recognition problem by one-shot…

A primary challenge when deploying speaker recognition systems in real-world applications is performance degradation caused by environmental mismatch. We propose a diffusion-based method that takes speaker embeddings extracted from a…

Parameterized mathematical models play a central role in understanding and design of complex information systems. However, they often cannot take into account the intricate interactions innate to such systems. On the contrary, purely…

Metric-based meta-learning has attracted a lot of attention due to its effectiveness and efficiency in few-shot learning. Recent studies show that metric scaling plays a crucial role in the performance of metric-based meta-learning…

Recent progress on end-to-end neural diarization (EEND) has enabled overlap-aware speaker diarization with a single neural network. This paper proposes to enhance EEND by using multi-channel signals from distributed microphones. We replace…

Healthcare foundation models have largely followed paradigms from natural language processing and computer vision, emphasizing large scale pretraining and deterministic representations over heterogeneous clinical data. However, clinical…

Diffusion models may be viewed as hierarchical variational autoencoders (VAEs) with two improvements: parameter sharing for the conditional distributions in the generative process and efficient computation of the loss as independent terms…

Healthcare data now span EHRs, medical imaging, genomics, and wearable sensors, but most diagnostic models still process these modalities in isolation. This limits their ability to capture early, cross-modal disease signatures. This paper…

The electroencephalogram (EEG) offers a non-invasive means by which a listener's auditory system may be monitored during continuous speech perception. Reliable auditory-EEG decoders could facilitate the objective diagnosis of hearing…

A key obstacle in automated analytics and meta-learning is the inability to recognize when different datasets contain measurements of the same variable. Because provided attribute labels are often uninformative in practice, this task may be…

Echocardiography (ECHO) video is widely used for cardiac examination. In clinical, this procedure heavily relies on operator experience, which needs years of training and maybe the assistance of deep learning-based systems for enhanced…

With the growing adoption of deep learning models in different real-world domains, including computational biology, it is often necessary to understand which data features are essential for the model's decision. Despite extensive recent…

Spread-spectrum signals are increasingly adopted in fields including communications, testing of electronic systems, Electro-Magnetic Compatibility (EMC) enhancement, ultrasonic non-destructive testing. This paper considers the synthesis of…

Stance detection is an important task, supporting many downstream tasks such as discourse parsing and modeling the propagation of fake news, rumors, and science denial. In this paper, we propose a novel framework for stance detection. Our…

With 95% of Internet traffic now encrypted, an effective approach to classifying this traffic is crucial for network security and management. This paper introduces ECHO -- a novel optimization process for ML/DL-based encrypted traffic…

Deep learning methods for unsupervised registration often rely on objectives that assume a uniform noise level across the spatial domain (e.g. mean-squared error loss), but noise distributions are often heteroscedastic and input-dependent…

Physiological signals such as electrocardiograms (ECG) and electroencephalograms (EEG) provide complementary insights into human health and cognition, yet multi-modal integration is challenging due to limited multi-modal labeled data, and…

The variational auto-encoder (VAE) is a popular method for learning a generative model and embeddings of the data. Many real datasets are hierarchically structured. However, traditional VAEs map data in a Euclidean latent space which cannot…

In an attempt to address the need for skilled clinicians in heart sound interpretation, recent research efforts on automating cardiac auscultation have explored deep learning approaches. The majority of these approaches have been based on…