Related papers: SPECTRE: Spectral Pre-training Embeddings with Cyl…

Spatiotemporal predictive learning (ST-PL) is a hotspot with numerous applications, such as object movement and meteorological prediction. It aims at predicting the subsequent frames via observed sequences. However, inherent uncertainty…

Network alignment consists of finding a structure-preserving correspondence between the nodes of two correlated, but not necessarily identical, networks. This problem finds applications in a wide variety of fields, from the alignment of…

Characterizing the long term behavior of dynamical systems given limited measurements is a common challenge throughout the physical and biological sciences. This is a challenging task due to the sparsity and noise inherent to empirical…

Classification of electroencephalogram (EEG) and electrocorticogram (ECoG) signals obtained during motor imagery (MI) has substantial application potential, including for communication assistance and rehabilitation support for patients with…

Multimodal large language models (MLLMs) have advanced from image-level reasoning to pixel-level grounding, but extending these capabilities to videos remains challenging as models must achieve spatial precision and temporally consistent…

In the field of Multi-Person Pose Estimation (MPPE), Radio Frequency (RF)-based methods can operate effectively regardless of lighting conditions and obscured line-of-sight situations. Existing RF-based MPPE methods typically involve either…

The growing exploration of Large Language Models (LLM) and Vision-Language Models (VLM) has opened avenues for enhancing the effectiveness of reinforcement learning (RL). However, existing LLM-based RL methods often focus on the guidance of…

Knowledge graph embedding (KGE) has become a fundamental technique for representation learning on multi-relational data. Many seminal models, such as TransE, operate in an unbounded Euclidean space, which presents inherent limitations in…

Self-supervised learning (SSL) methods such as masked language modeling have shown massive performance gains by pretraining transformer models for a variety of natural language processing tasks. The follow-up research adapted similar…

EEG signals capture brain activity with high temporal and low spatial resolution, supporting applications such as neurological diagnosis, cognitive monitoring, and brain-computer interfaces. However, effective analysis is hindered by…

Restoring limb motor function in individuals with spinal cord injury (SCI), stroke, or amputation remains a critical challenge, one which affects millions worldwide. Recent studies show through surface electromyography (EMG) that spared…

Scene text recognition (STR) pre-training methods have achieved remarkable progress, primarily relying on synthetic datasets. However, the domain gap between synthetic and real images poses a challenge in acquiring feature representations…

Quantum kernel methods are promising for near-term quantum ma- chine learning, yet their behavior under data corruption remains insuf- ficiently understood. We analyze how quantum feature constructions degrade under controlled additive…

This study investigates the impact of electrode shift and sensor reapplication on common surface electromyography (sEMG) features in lower limb muscles, factors which have, thus far, precluded clinicians from being able to attribute…

Walking-assistive devices require adaptive control methods to ensure smooth transitions between various modes of locomotion. For this purpose, detecting human locomotion modes (e.g., level walking or stair ascent) in advance is crucial for…

Confocal laser endomicroscopy (CLE) is a non-invasive, real-time imaging modality that can be used for in-situ, in-vivo imaging and the microstructural analysis of mucous structures. The diagnosis using CLE is, however, complicated by…

Magnetic Resonance Fingerprinting (MRF) enables fast quantitative imaging, yet reconstructing high-resolution 3D data remains computationally demanding. Non-Cartesian reconstructions require repeated non-uniform FFTs, and the commonly used…

Temporal Forgery Localization (TFL) aims to precisely identify manipulated segments in video and audio, offering strong interpretability for security and forensics. While recent State Space Models (SSMs) show promise in precise temporal…

Spatio-temporal trajectories provide valuable information about movement and travel behavior, enabling various downstream tasks that in turn power real-world applications. Learning trajectory embeddings can improve task performance but may…

While end-to-end multi-channel electroencephalography (EEG) learning approaches have shown significant promise, their applicability is often constrained in neurological diagnostics, such as intracranial EEG resources. When provided with a…