Related papers: Sparse Multi-Modal Transformer with Masking for Al…

Few-shot classification and segmentation (FS-CS) focuses on jointly performing multi-label classification and multi-class segmentation using few annotated examples. Although the current state of the art (SOTA) achieves high accuracy in both…

Multimodal sensors provide complementary information to develop accurate machine-learning methods for human activity recognition (HAR), but introduce significantly higher computational load, which reduces efficiency. This paper proposes an…

Treatment switching is a common occurrence in the management of Multiple Sclerosis (MS), where patients transition across various disease-modifying therapies (DMTs) due to heterogeneous treatment responses, differences in disease…

Multimodal neuroimaging provides complementary structural and functional insights into both human brain organization and disease-related dynamics. Recent studies demonstrate enhanced diagnostic sensitivity for Alzheimer's disease (AD)…

Transformer models have achieved state-of-the-art results in a wide range of NLP tasks including summarization. Training and inference using large transformer models can be computationally expensive. Previous work has focused on one…

Although transformer is preferred in natural language processing, some studies has only been applied to the field of medical imaging in recent years. For its long-term dependency, the transformer is expected to contribute to unconventional…

Large Language Models (LLMs) such as LLaMA and DeepSeek, are built on transformer architectures, which have become a standard model for achieving state-of-the-art performance in natural language processing tasks. Recently, there has been…

Recently, neural machine translation has achieved remarkable progress by introducing well-designed deep neural networks into its encoder-decoder framework. From the optimization perspective, residual connections are adopted to improve…

As wireless communication systems evolve, automatic modulation recognition (AMR) plays a key role in improving spectrum efficiency, especially in cognitive radio systems. Traditional AMR methods face challenges in complex, noisy…

Transformer models rely on Multi-Head Self-Attention (MHSA) mechanisms, where each attention head contributes to the final representation. However, their computational complexity and high memory demands due to MHSA hinders their deployment…

Spiking neural networks (SNNs) have emerged as a promising candidate for energy-efficient LLM inference. However, current energy evaluations for SNNs primarily focus on counting accumulate operations, and fail to account for real-world…

Structured sparsity enables deploying large language models (LLMs) on resource-constrained systems. Approaches like dense-to-sparse fine-tuning are particularly compelling, achieving remarkable structured sparsity by reducing the model size…

The transformer architecture has driven breakthroughs in recent years on tasks which require modeling pairwise relationships between sequential elements, as is the case in natural language understanding. However, long seqeuences pose a…

Despite the recent progress in speech emotion recognition (SER), state-of-the-art systems are unable to achieve improved performance in cross-language settings. In this paper, we propose a Multimodal Dual Attention Transformer (MDAT) model…

The attention mechanism within the transformer architecture enables the model to weigh and combine tokens based on their relevance to the query. While self-attention has enjoyed major success, it notably treats all queries $q$ in the same…

In this paper, we introduce \texttt{IAFormer}, a novel Transformer-based architecture that efficiently integrates pairwise particle interactions through a dynamic sparse attention mechanism. \texttt{IAFormer} has two new mechanisms within…

Predicting whether subjects with mild cognitive impairment (MCI) will convert to Alzheimer's disease is a significant clinical challenge. Longitudinal variations and complementary information inherent in longitudinal and multimodal data are…

Alzheimer's disease (AD) is the most prevalent neurodegenerative disease; yet its currently available treatments are limited to stopping disease progression. Moreover, effectiveness of these treatments is not guaranteed due to the…

Multimodal data fusion is essential for applications requiring the integration of diverse data sources, especially in the presence of incomplete or sparsely available modalities. This paper presents a comparative study of three multimodal…

Sparsity-aware training is an effective approach for transforming large language models (LLMs) into hardware-friendly sparse patterns, thereby reducing latency and memory consumption during inference. In this paper, we propose Continuous…