As the deep learning revolution marches on, self-supervised learning has garnered
increasing attention in recent years thanks to its remarkable representation learning ability …

We all know that large language models are built on top of a transformer-based architecture
to process textual inputs. For example, the LLaMA family of models stands out among many …

We propose to improve transformers of a specific modality with irrelevant data from other
modalities eg improve an ImageNet model with audio or point cloud datasets. We would like …

Abstract Audio-Visual Emotion Recognition (AVER) has garnered increasing attention in
recent years for its critical role in creating emotion-aware intelligent machines. Previous …

Masked Image Modeling (MIM) has achieved promising progress with the advent of Masked
Autoencoders (MAE) and BEiT. However, subsequent works have complicated the …

Expert annotation of 3D medical image for downstream analysis is resource-intensive,
posing challenges in clinical applications. Visual self-supervised learning (vSSL), though …

Recently the advancement of self-supervised learning techniques like masked
autoencoders (MAE) has greatly influenced visual representation learning for images and …

Electrocardiograms (ECGs) are non-invasive diagnostic tools crucial for detecting cardiac
arrhythmic diseases in clinical practice. While ECG Self-supervised Learning (eSSL) …

Large language models are built on top of a transformer-based architecture to process
textual inputs. For example, the LLaMA stands out among many open-source …

Images suffer from heavy spatial redundancy because pixels in neighboring regions are
spatially correlated. Existing approaches strive to overcome this limitation by reducing less …