Related papers: Multi-Architecture Multi-Expert Diffusion Models
Semantic communication is emerging as a key enabler for distributed edge intelligence due to its capability to convey task-relevant meaning. However, achieving communication-efficient training and robust inference over wireless links…
In [1], we introduced a new, matrix algebraic, performance analysis framework for wireless systems with fading channels based on the matrix exponential distribution. The main idea was to use the compact, powerful, and easy-to-use, matrix…
Diffusion Models have become a cornerstone of modern generative AI for their exceptional generation quality and controllability. However, their inherent \textit{multi-step iterations} and \textit{complex backbone networks} lead to…
It is widely acknowledged that the performance of Transformer models is logarithmically related to their number of parameters and computational complexity. While approaches like Mixture of Experts (MoE) decouple parameter count from…
The recent success of specialized Large Language Models (LLMs) in domains such as mathematical reasoning and coding has led to growing interest in methods for merging these expert LLMs into a unified Mixture-of-Experts (MoE) model, with the…
The presented article contains a 3D mesh generation routine optimized with the Metropolis algorithm. The procedure enables to produce meshes of a prescribed volume V_0 of elements. The finite volume meshes are used with the Finite Element…
Diffusion models have shown remarkable capabilities in generating high-fidelity data across modalities such as images, audio, and video. However, their computational intensity makes deployment on edge devices a significant challenge. This…
Diffusion-based generative models (DBGMs) perturb data to a target noise distribution and reverse this process to generate samples. The choice of noising process, or inference diffusion process, affects both likelihoods and sample quality.…
Recent diffusion-based methods for material transfer rely on image fine-tuning or complex architectures with assistive networks, but face challenges including text dependency, extra computational costs, and feature misalignment. To address…
Mixture-of-Experts (MoE) models enable scalable performance by activating large parameter sets sparsely, minimizing computational overhead. To mitigate the prohibitive cost of training MoEs from scratch, recent work employs upcycling,…
MoE-PEFT methods combine Mixture of Experts with parameter-efficient fine-tuning for multi-task adaptation, but require separate adapters per expert causing trainable parameters to scale linearly with expert count and limiting applicability…
Mixture-of-Experts (MoE) models improve the scalability of large language models (LLMs) by activating only a small subset of relevant experts per input. However, the sheer number of expert networks in an MoE model introduces a significant…
Mixture-of-Experts (MoE) architectures offer the promise of larger model capacity without the prohibitive costs of fully dense designs. However, in real-world inference serving, load skew across experts often leads to suboptimal device…
Recent studies show that using diffusion models for time series signal reconstruction holds great promise. However, such approaches remain largely unexplored in the domain of medical time series. The unique characteristics of the…
Denoising Diffusion Models (DDMs) have become a popular tool for generating high-quality samples from complex data distributions. These models are able to capture sophisticated patterns and structures in the data, and can generate samples…
The performance of deep learning models is critically dependent on sophisticated optimization strategies. While existing optimizers have shown promising results, many rely on first-order Exponential Moving Average (EMA) techniques, which…
Mixture-of-Experts (MoE) models typically fix the number of activated experts $k$ at both training and inference. However, real-world deployments often face heterogeneous hardware, fluctuating workloads, and diverse quality-latency…
Image fusion is a fundamental and important task in computer vision, aiming to combine complementary information from different modalities to fuse images. In recent years, diffusion models have made significant developments in the field of…
Diffusion models have recently gained unprecedented attention in the field of image synthesis due to their remarkable generative capabilities. Notwithstanding their prowess, these models often incur substantial computational costs,…
Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains. However, current foundation FM models are computationally prohibitive for…