Related papers: Mixture-of-Experts Diffusion Models for Adaptive M…

Model editing aims to efficiently alter the behavior of Large Language Models (LLMs) within a desired scope, while ensuring no adverse impact on other inputs. Recent years have witnessed various model editing methods been proposed. However,…

The expansion of large language models is increasingly limited by the constrained memory capacity of modern GPUs. To mitigate this, Mixture-of-Experts (MoE) architectures activate only a small portion of parameters during inference,…

Mixture-of-Experts (MoE) models offer dynamic computation, but are typically deployed as static full-capacity models, missing opportunities for deployment-specific specialization. We introduce PreMoE, a training-free framework that…

Vision Transformers have emerged as the state-of-the-art models in various Computer Vision tasks, but their high computational and resource demands pose significant challenges. While Mixture-of-Experts (MoE) can make these models more…

Generative Artificial Intelligence (GenAI) models, with their powerful feature learning capabilities, have been applied in many fields. In mobile wireless communications, GenAI can dynamically optimize the network to enhance the user…

Mixture-of-Experts (MoE) models scale large language models efficiently by sparsely activating experts, but once an expert is selected, it is executed fully. Hence, the trade-off between accuracy and computation in an MoE model typically…

In this paper, adaptive hybrid beamforming methods are proposed for millimeter-wave range massive multiple-input-multiple-output (MIMO) systems considering single carrier wideband transmission in uplink data mode. A statistical analog…

Estimating accurate and well-calibrated predictive uncertainty is important for enhancing the reliability of computer vision models, especially in safety-critical applications like traffic scene perception. While ensemble methods are…

The problem of modulation classification for a multiple-antenna (MIMO) system employing orthogonal frequency division multiplexing (OFDM) is investigated under the assumption of unknown frequency-selective fading channels and…

Clinical decision-making reflects diverse strategies shaped by regional patient populations and institutional protocols. However, most existing medical artificial intelligence (AI) models are trained on highly prevalent data patterns, which…

End-to-end models with large capacity have significantly improved multilingual automatic speech recognition, but their computation cost poses challenges for on-device applications. We propose a streaming truly multilingual Conformer…

Foundation models for medical image segmentation have achieved remarkable performance. Adaptive fine-tuning of natural image segmentation foundation models is crucial for medical image segmentation tasks. However, some limitations exist in…

Millimeter Wave (mmWave) massive Multiple Input Multiple Output (MIMO) systems realizing directive beamforming require reliable estimation of the wireless propagation channel. However, mmWave channels are characterized by high variability…

We present Bayesian Diffusion Models (BDM), a prediction algorithm that performs effective Bayesian inference by tightly coupling the top-down (prior) information with the bottom-up (data-driven) procedure via joint diffusion processes. We…

Massive MIMO (mMIMO) systems are essential for 5G/6G networks to meet high throughput and reliability demands, with machine learning (ML)-based techniques, particularly autoencoders (AEs), showing promise for practical deployment. However,…

As the Mix-of-Experts (MoE) architecture increases the number of parameters in large models, there is an even greater need for model quantization. However, existing quantization methods overlook the expert dynamics of MoE across multiple…

We study the expectation propagation (EP) algorithm for symbol detection in massive multiple-input multiple-output (MIMO) systems. The EP detector shows excellent performance but suffers from a high computational complexity due to the…

In recent years, Mixture-of-Experts (MoE) has emerged as an effective approach for enhancing the capacity of deep neural network (DNN) with sub-linear computational costs. However, storing all experts on GPUs incurs significant memory…

Multimodal variational autoencoders have demonstrated their ability to learn the relationships between different modalities by mapping them into a latent representation. Their design and capacity to perform any-to-any conditional and…

Diffusion models have demonstrated remarkable success in various image generation tasks, but their performance is often limited by the uniform processing of inputs across varying conditions and noise levels. To address this limitation, we…