Related papers: BeatFM: Improving Beat Tracking with Pre-trained M…
Recent advancements in music large language models (LLMs) have significantly improved music understanding tasks, which involve the model's ability to analyze and interpret various musical elements. These improvements primarily focused on…
Knowledge Tracing is the process of tracking mastery level of different skills of students for a given learning domain. It is one of the key components for building adaptive learning systems and has been investigated for decades. In…
Automatic drum transcription is a critical tool in Music Information Retrieval for extracting and analyzing the rhythm of a music track, but it is limited by the size of the datasets available for training. A popular method used to increase…
Beat-level Electrocardiography (ECG) arrhythmia detection aims to assign an arrhythmia class to each beat in a recording, yet many existing systems treat beats as isolated local instances. This is limiting because beat labels often depend…
Electroencephalography (EEG) signals provide critical insights for applications in disease diagnosis and healthcare. However, the scarcity of labeled EEG data poses a significant challenge. Foundation models offer a promising solution by…
Following its success for vision and text, the "foundation model" (FM) paradigm -- pretraining large models on massive data, then fine-tuning on target tasks -- has rapidly expanded to domains in the sciences, engineering, healthcare, and…
Machine learning models in astrophysics are often limited in scope and cannot adapt to data from new instruments or tasks. We introduce SpectraFM, a Transformer-based foundation model architecture that can be pre-trained on stellar spectra…
Masked token prediction has emerged as a powerful pre-training objective across language, vision, and speech, offering the potential to unify these diverse modalities through a single pre-training task. However, its application for general…
Multimodal semantic segmentation shows significant potential for enhancing segmentation accuracy in complex scenes. However, current methods often incorporate specialized feature fusion modules tailored to specific modalities, thereby…
Brain Foundation Models (BFMs) are transforming neuroscience by enabling scalable and transferable learning from neural signals, advancing both clinical diagnostics and cutting-edge neuroscience exploration. Their emergence is powered by…
Lack of large-scale note-level labeled data is the major obstacle to singing transcription from polyphonic music. We address the issue by using pseudo labels from vocal pitch estimation models given unlabeled data. The proposed method first…
State estimation remains a fundamental challenge across numerous domains, from autonomous driving, aircraft tracking to quantum system control. Although Bayesian filtering has been the cornerstone solution, its classical model-based…
Multi-instrument Automatic Music Transcription (AMT), or the decoding of a musical recording into semantic musical content, is one of the holy grails of Music Information Retrieval. Current AMT approaches are restricted to piano and (some)…
Multi-object tracking (MOT) is a fundamental task in computer vision that requires continuously tracking multiple targets while maintaining consistent identities across frames. However, most existing approaches primarily rely on…
Music representations are the backbone of modern recommendation systems, powering playlist generation, similarity search, and personalized discovery. Yet most embeddings offer little control for adjusting a single musical attribute, e.g.,…
Foundational models are trained on extensive datasets to capture the general trends of a domain. However, in medical imaging, the scarcity of data makes pre-training for every domain, modality, or task challenging. Instead of building…
Topic models are a popular approach for extracting semantic information from large document collections. However, recent studies suggest that the topics generated by these models often do not align well with human intentions. Although…
Cardiac biosignals, such as electrocardiograms (ECG) and photoplethysmograms (PPG), are of paramount importance for the diagnosis, prevention, and management of cardiovascular diseases, and have been extensively used in a variety of…
Multiple Object Tracking (MOT) has rapidly progressed in recent years. Existing works tend to design a single tracking algorithm to perform both detection and association. Though ensemble learning has been exploited in many tasks, i.e,…
Foundation models (FMs) have emerged as a powerful paradigm, enabling a diverse range of data analytics and knowledge discovery tasks across scientific fields. Inspired by the success of FMs, particularly large language models, researchers…