相关论文: Synthesis models in the VO framework

In network management, when it comes to security breaches, human error constitutes a dominant factor. We present our tool topoS which automatically synthesizes low-level network configurations from high-level security goals. The automation…

In recent years, a large number of binarization methods have been developed, with varying performance generalization and strength against different benchmarks. In this work, to leverage on these methods, an ensemble of experts (EoE)…

We present a novel introspective variational autoencoder (IntroVAE) model for synthesizing high-resolution photographic images. IntroVAE is capable of self-evaluating the quality of its generated samples and improving itself accordingly.…

With the growing complexity of deep learning methods adopted in practical applications, there is an increasing and stringent need to explain and interpret the decisions of such methods. In this work, we focus on explainable AI and propose a…

The International Virtual Observatory Alliance (IVOA) held its bi-annual Interoperability Meetings in May 2019, and in October 2019 following the ADASS XXIX conference. We provide a brief report on the status of the IVOA and the activities…

Diffusion Models are probabilistic models that create realistic samples by simulating the diffusion process, gradually adding and removing noise from data. These models have gained popularity in domains such as image processing, speech…

An IVOA Identifier is a globally unique name for a resource within the Virtual Observatory. This name can be used to retrieve a unique description of the resource from an IVOA-compliant registry or to identify an entity like a dataset or a…

Global MCAO aims to exploit a very wide technical field of view to find AO-suitable NGSs, with the goal to increase the overall sky coverage. The concept foresees the use of numerical entities, called Virtual Deformable Mirrors, to deal…

This paper presents an interaction model adapted to mixed reality environments known as IRVO (Interacting with Real and Virtual Objects). IRVO aims at modeling the interaction between one or more users and the Mixed Reality system by…

In this paper, we introduce semi-supervised video object segmentation (VOS) to panoptic wild scenes and present a large-scale benchmark as well as a baseline method for it. Previous benchmarks for VOS with sparse annotations are not…

We present new evolutionary synthesis models for Simple Stellar Populations for a wide range of ages and metallicities. The models are based on the Padova isochrones. The core of the spectral library is provided by the medium resolution…

Registries provide a mechanism with which VO applications can discover and select resources--e.g. data and services--that are relevant for a particular scientific problem. This specification defines the interfaces that support interactions…

Reliable verifiable data has become a key driver of capability gains in modern language models, enabling stable reinforcement learning with verifiable rewards and effective distillation that transfers competence across math, coding, and…

With the rapid advancement of synthetic dataset generation techniques, evaluating the quality of synthetic data has become a critical research focus. Robust evaluation not only drives innovations in data generation methods but also guides…

Variational autoencoders (VAEs) are a popular class of deep generative models with many variants and a wide range of applications. Improvements upon the standard VAE mostly focus on the modelling of the posterior distribution over the…

Real-world data often exhibits bias, imbalance, and privacy risks. Synthetic datasets have emerged to address these issues. This paradigm relies on generative AI models to generate unbiased, privacy-preserving data while maintaining…

This work presents a new framework for procedural generation of dynamic 3D plant model geometries, which has been implemented in the Helios modeling system. Key goals of this work were to develop a model that 1) has a generalized set of…

Ensuring the generalisability of clinical machine learning (ML) models across diverse healthcare settings remains a significant challenge due to variability in patient demographics, disease prevalence, and institutional practices. Existing…

Variability management (VM) in software product line engineering (SPLE) is introduced as an abstraction that enables the reuse and customization of assets. VM is a complex task involving the identification, representation, and instantiation…

Recent advances in diffusion-based video generation have opened new possibilities for controllable video editing, yet realistic video object insertion (VOI) remains challenging due to limited 4D scene understanding and inadequate handling…