Score-based diffusion models are a class of generative models whose dynamics is described by stochastic differential equations that map noise into data. While recent works have started to lay down a theoretical foundation for these models, a detailed understanding of the role of the diffusion time T is still lacking. Current best practice advocates for a large T to ensure that the forward dynamics brings the diffusion sufficiently close to a known and simple noise distribution; however, a smaller value of T should be preferred for a better approximation of the score-matching objective and higher computational efficiency. Starting from a variational interpretation of diffusion models, in this work we quantify this trade-off and suggest a new method to improve quality and efficiency of both training and sampling, by adopting smaller diffusion times. Indeed, we show how an auxiliary model can be used to bridge the gap between the ideal and the simulated forward dynamics, followed by a standard reverse diffusion process. Empirical results support our analysis; for image data, our method is competitive with regard to the state of the art, according to standard sample quality metrics and log-likelihood.

Multimodal datasets are ubiquitous in modern applications, and multimodal Variational Autoencoders are a popular family of models that aim to learn a joint representation of different modalities. However, existing approaches suffer from a coherence–quality tradeoff in which models with good generation quality lack generative coherence across modalities and vice versa. In this paper, we discuss the limitations underlying the unsatisfactory performance of existing methods in order to motivate the need for a different approach. We propose a novel method that uses a set of independently trained and unimodal deterministic autoencoders. Individual latent variables are concatenated into a common latent space, which is then fed to a masked diffusion model to enable generative modeling. We introduce a new multi-time training method to learn the conditional score network for multimodal diffusion. Our methodology substantially outperforms competitors in both generation quality and coherence, as shown through an extensive experimental campaign.

In the upcoming 6G era, mobile networks must deal with more challenging applications (e.g., holographic telepresence and immersive communication) and meet far more stringent application requirements stemming along the edge-cloud continuum. These new applications will create an elevated level of expectations on performance, reliability, ubiquity, trust-worthiness, security, openness, and sustainability, pushing the boundaries of innovation and driving transformational change across the architecture of future mobile networks. Towards this end, ADROIT6G proposes a set of disruptive innovations with a clear vision on setting a 6G network architecture that can be tailored to the requirements of innovative applications and match the ambitious KPls set for 6G networks. More specifically, the key transformations that ADROIT6G considers essential to 6G network evolution are: i) AIIML-powered optimisations across the network, exploring solutions in the “Distributed Artificial Intelligence (DAI)” domain for high performance and automation; ii) Transforming to fully cloud-native network software, which can be implemented across various edge-cloud platforms, with security built integrally into the network user plan; and iii) Soft-ware driven, zero-touch operations and ultimately automation of every aspect of the network and the services it delivers.

Synthetic DNA has received much attention recently as a long-term archival medium alternative due to its high density and durability characteristics. However, most current work has primarily focused on using DNA as a precise storage medium. In this work, we take an alternate view of DNA. Using neural-network-based compression techniques, we transform images into a latent-space representation, which we then store on DNA. By doing so, we transform DNA into an approximate image storage medium, as images generated back from DNA are only approximate representations of the original images. Using several datasets, we investigate the storage benefits of approximation, and study the impact of DNA storage errors (substitutions, indels, bias) on the quality of approximation. In doing so, we demonstrate the feasibility and potential of viewing DNA as an approximate storage medium.

This work focuses on a machine learning based detection of ionospheric scintillation events affecting Global Navigation Satellite System (GNSS) signals. We here extend the recent detection results based on Decision Trees, designing a semi-supervised detection system based on the DeepInfomax approach recently proposed. The paper shows that it is possible to achieve good classification accuracy while reducing the amount of time that human experts must spend manually labelling the datasets for the training of supervised algorithms. The proposed method is scalable and reduces the required percentage of annotated samples to achieve a given performance, making it a viable candidate for a realistic deployment of scintillation detection in software defined GNSS receivers.

Diffusion models have recently emerged as a powerful class of generative models, achieving state-of-the-art performance in various domains such as image and audio synthesis. While most existing work focuses on finite-dimensional data, there is growing interest in extending diffusion models to infinite-dimensional function spaces. This survey provides a comprehensive overview of the theoretical foundations and practical applications of diffusion models in infinite dimensions. We review the necessary background on stochastic differential equations in Hilbert spaces, and then discuss different approaches to define generative models rooted in such formalism. Finally, we survey recent applications of infinite-dimensional diffusion models in areas such as generative modelling for function spaces, conditional generation of functional data and solving inverse problems. Throughout the survey, we highlight the connections between different approaches and discuss open problems and future research directions. This article is part of the theme issue ‘Generative modelling meets Bayesian inference: a new paradigm for inverse problems’.