Related papers: From Transthoracic to Transesophageal: Cross-Modal…

Score-based diffusion modeling is a generative machine learning algorithm that can be used to sample from complex distributions. They achieve this by learning a score function, i.e., the gradient of the log-probability density of the data,…

Diffusion models have achieved remarkable image generation quality surpassing previous generative models. However, a notable limitation of diffusion models, in comparison to GANs, is their difficulty in smoothly interpolating between two…

Diffusion-based Generative AI gains significant attention for its superior performance over other generative techniques like Generative Adversarial Networks and Variational Autoencoders. While it has achieved notable advancements in fields…

Large language models (LLMs) encounter significant adaptation challenges in diverse multitask finetuning. Mixture-of-experts (MoE) provides a promising solution with a dynamic architecture, enabling effective task decoupling. However,…

Class-incremental learning is dedicated to the development of deep learning models that are capable of acquiring new knowledge while retaining previously learned information. Most methods focus on balanced data distribution for each task,…

MRI cross-modal synthesis involves generating images from one acquisition protocol using another, offering considerable clinical value by reducing scan time while maintaining diagnostic information. This paper presents a comprehensive…

Missing input sequences are common in medical imaging data, posing a challenge for deep learning models reliant on complete input data. In this work, inspired by MultiMAE [2], we develop a masked autoencoder (MAE) paradigm for multi-modal,…

Counterfactual explanations (CEs) aim to enhance the interpretability of machine learning models by illustrating how alterations in input features would affect the resulting predictions. Common CE approaches require an additional model and…

Conventional class-guided diffusion models generally succeed in generating images with correct semantic content, but often struggle with texture details. This limitation stems from the usage of class priors, which only provide coarse and…

The mixture-of-experts (MoE) architecture, which replaces dense networks with sparse ones, has attracted significant attention in large vision-language models (LVLMs) for achieving comparable performance while activating far fewer…

The demonstrated success of sparsely-gated Mixture-of-Experts (MoE) architectures, exemplified by models such as DeepSeek and Grok, has motivated researchers to investigate their adaptation to diverse domains. In real-world image…

Scaling the size of a model enhances its capabilities but significantly increases computation complexity. Mixture-of-Experts models (MoE) address the issue by allowing model size to scale up without substantially increasing training or…

Automated emotion detection in speech is a challenging task due to the complex interdependence between words and the manner in which they are spoken. It is made more difficult by the available datasets; their small size and incompatible…

Deep learning is widely applied in computer-aided pathological diagnosis, which alleviates the pathologist workload and provide timely clinical analysis. However, most models generally require large-scale annotated data for training, which…

Driven by the evolution toward 6G and AI-native edge intelligence, network operations increasingly require predictive and risk-aware adaptation under stringent computation and latency constraints. Network Traffic Matrix (TM), which…

Large Language Models (LLMs) have significantly advanced molecular discovery, but existing multimodal molecular architectures fundamentally rely on autoregressive (AR) backbones. This strict left-to-right inductive bias is sub-optimal for…

Mixture-of-Experts (MoE) has emerged as a powerful framework for multi-task learning (MTL). However, existing MoE-MTL methods often rely on single-task pretrained backbones and suffer from redundant adaptation and inefficient knowledge…

Deep neural networks have achieved remarkable success in a variety of computer vision applications. However, there is a problem of degrading accuracy when the data distribution shifts between training and testing. As a solution of this…

Diffusion-based representation learning has achieved substantial attention due to its promising capabilities in latent representation and sample generation. Recent studies have employed an auxiliary encoder to identify a corresponding…

Multimodal generative models require a unified approach to handle both discrete data (e.g., text and code) and continuous data (e.g., image, audio, video). In this work, we propose Latent Language Modeling (LatentLM), which seamlessly…