Related papers: FOAA: Flattened Outer Arithmetic Attention For Mul…

Foundation models open up new possibilities for the use of AI in healthcare. However, even when pre-trained on health data, they still need to be fine-tuned for specific downstream tasks. Furthermore, although foundation models reduce the…

Analysis of somatic mutation profiles from cancer patients is essential in the development of cancer research. However, the low frequency of most mutations and the varying rates of mutations across patients makes the data extremely…

Transformer self-attention computes pairwise token interactions, yet protein sequence to phenotype relationships often involve cooperative dependencies among three or more residues that dot product attention does not capture explicitly. We…

Technological advances in medical data collection, such as high-throughput genomic sequencing and digital high-resolution histopathology, have contributed to the rising requirement for multimodal biomedical modelling, specifically for…

Multimodal intent understanding is a significant research area that requires effective leveraging of multiple modalities to analyze human language. Existing methods face two main challenges in this domain. Firstly, they have limitations in…

Understanding multimodal perception for embodied AI is an open question because such inputs may contain highly complementary as well as redundant information for the task. A relevant direction for multimodal policies is understanding the…

With the growing application of transformer in computer vision, hybrid architecture that combine convolutional neural networks (CNNs) and transformers demonstrates competitive ability in medical image segmentation. However, direct fusion of…

Inspired by the recent success of the Mamba architecture in vision and language domains, we introduce a Unified Attention-Mamba (UAM) backbone. Unlike previous hybrid approaches that integrate Attention and Mamba modules in fixed…

Most convolutional neural network (CNN) based methods for skin cancer classification obtain their results using only dermatological images. Although good classification results have been shown, more accurate results can be achieved by…

Visual question answering (VQA) is challenging because it requires a simultaneous understanding of both the visual content of images and the textual content of questions. The approaches used to represent the images and questions in a…

In recent years, multi-objective optimization (MOO) emerges as a foundational problem underpinning many multi-agent multi-task learning applications. However, existing algorithms in MOO literature remain limited to centralized learning…

Attention mechanisms are widely used in current encoder/decoder frameworks of image captioning, where a weighted average on encoded vectors is generated at each time step to guide the caption decoding process. However, the decoder has…

Detecting out-of-distribution (OOD) data is crucial in machine learning applications to mitigate the risk of model overconfidence, thereby enhancing the reliability and safety of deployed systems. The majority of existing OOD detection…

Automatic breast lesion detection and classification is an important task in computer-aided diagnosis, in which breast ultrasound (BUS) imaging is a common and frequently used screening tool. Recently, a number of deep learning-based…

Attention with bias, which extends standard attention by introducing prior knowledge as an additive bias matrix to the query-key scores, has been widely deployed in vision, language, protein-folding and other advanced scientific models,…

AI-assisted radiological interpretation is based on predominantly narrow, single-task models. This approach is impractical for covering the vast spectrum of imaging modalities, diseases, and radiological findings. Foundation models (FMs)…

The application of machine learning methods to analyze changes in gene expression patterns has recently emerged as a powerful approach in cancer research, enhancing our understanding of the molecular mechanisms underpinning cancer…

Recent research has made significant progress in designing fusion modules for audio-visual speech separation. However, they predominantly focus on multi-modal fusion at a single temporal scale of auditory and visual features without…

Acquiring high-quality Positron Emission Tomography (PET) images requires administering high-dose radiotracers, which increases radiation exposure risks. Generating standard-dose PET (SPET) from low-dose PET (LPET) has become a potential…

One of appealing approaches to guiding learnable parameter optimization, such as feature maps, is global attention, which enlightens network intelligence at a fraction of the cost. However, its loss calculation process still falls short:…