Related papers: ConceptM$^3$oE: Concept-Guided Multimodal Mixture …

Many interpretable AI approaches have been proposed to provide plausible explanations for a model's decision-making. However, configuring an explainable model that effectively communicates among computational modules has received less…

Mixture of experts (MoE) architectures have become a cornerstone for scaling up and are a key component in most large language models such as GPT-OSS, DeepSeek-V3, Llama-4, and Gemini-2.5. However, systematic research on MoE remains…

Knowledge editing (KE) provides a scalable approach for updating factual knowledge in large language models without full retraining. While previous studies have demonstrated effectiveness in general domains and medical QA tasks, little…

The relentless scaling of deep learning models has led to unsustainable computational demands, positioning Mixture-of-Experts (MoE) architectures as a promising path towards greater efficiency. However, MoE models are plagued by two…

Cancer diagnosis, prognosis, and therapeutic response predictions are based on morphological information from histology slides and molecular profiles from genomic data. However, most deep learning-based objective outcome prediction and…

Sparse Mixture-of-Experts (MoE) architectures route each token through a subset of experts at each layer independently. We propose viewing MoE computation through the lens of \emph{expert paths} -- the sequence of expert selections a token…

The opaque nature of deep learning models remains a significant barrier to their clinical adoption in medical imaging. This paper presents a multimodal explainability framework that bridges the gap between convolutional neural network (CNN)…

Unified multimodal large language models (MLLMs) based on end-to-end autoregressive (AR) transformers effectively integrate both understanding and generation tasks within a single framework. However, intrinsic Task Objective Conflicts…

Objective: To transform heterogeneous clinical data from electronic health records into clinically meaningful constructed features using data driven method that rely, in part, on temporal relations among data. Materials and Methods: The…

Decoding visual experiences from fMRI offers a powerful avenue to understand human perception and develop advanced brain-computer interfaces. However, current progress often prioritizes maximizing reconstruction fidelity while overlooking…

Mixture-of-Experts (MoE) models have gained popularity as a means of scaling the capacity of large language models (LLMs) while maintaining sparse activations and reduced per-token compute. However, in memory-constrained inference settings,…

Reliable channel estimation (CE) is fundamental for robust communication in dynamic wireless environments, where models must generalize across varying conditions such as signal-to-noise ratios (SNRs), the number of resource blocks (RBs),…

The advent of Large Language Models (LLMs) has ushered in a new era of artificial intelligence, with the potential to transform various sectors through automation and insightful analysis. The Mixture of Experts (MoE) architecture has been…

Learning a robust Variational Autoencoder (VAE) is a fundamental step for many deep learning applications in medical image analysis, such as MRI synthesizes. Existing brain VAEs predominantly focus on single-modality data (i.e., T1-weighted…

Recently, mixture of experts (MoE) has become a popular paradigm for achieving the trade-off between modal capacity and efficiency of multi-modal large language models (MLLMs). Different from previous efforts, we are dedicated to exploring…

Recently, Mixture-of-Experts (MoE) models have gained attention for efficiently scaling large language models. Although these models are extremely large, their sparse activation enables inference to be performed by accessing only a fraction…

Representation learning on electronic health records (EHRs) plays a vital role in downstream medical prediction tasks. Although natural language processing techniques, such as recurrent neural networks, and self-attention, have been adapted…

Recent advancements in all-in-one image restoration models have revolutionized the ability to address diverse degradations through a unified framework. However, parameters tied to specific tasks often remain inactive for other tasks, making…

Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs). Although Mixture-of-Experts (MoE) architectures offer an efficient path to scaling, existing…

While traditional self-supervised learning methods improve performance and robustness across various medical tasks, they rely on single-vector embeddings that may not capture fine-grained concepts such as anatomical structures or organs.…