Related papers: The Case for Multi-Version Experimental Evaluation…

Machine learning (ML) components are being added to more and more critical and impactful software systems, but the software development process of real-world production systems from prototyped ML models remains challenging with additional…

We introduce Differential Performance Evaluation (DPE), a framework designed to reliably evaluate Large Language Models (LLMs) for efficient code generation. Traditional coding benchmarks often fail to provide reliable insights into code…

The potential disconnect between research and practice in software engineering (SE) means that the uptake of research outcomes has at times been limited. In this paper we seek to identify research approaches that are rigorous in terms of…

Deep ensembles (DE) have been successful in improving model performance by learning diverse members via the stochasticity of random initialization. While recent works have attempted to promote further diversity in DE via hyperparameters or…

Large Language Models (LLMs) excel at code generation but remain heavily reliant on large-scale annotated solutions and verification-based supervision, which constrains scalability and hinders sustained self-improvement. Recent…

This paper presents VAEneu, an innovative autoregressive method for multistep ahead univariate probabilistic time series forecasting. We employ the conditional VAE framework and optimize the lower bound of the predictive distribution…

Structural modeling is a fundamental component of computational engineering science, in which even minor physical inconsistencies or specification violations may invalidate downstream simulations. The potential of large language models…

[Background] The MVP concept has influenced the way in which development teams apply Software Engineering practices. However, the overall understanding of this influence of MVPs on SE practices is still poor. [Objective] Our goal is to…

This paper aims to conduct a comparative analysis of contemporary Variational Autoencoder (VAE) architectures employed in anomaly detection, elucidating their performance and behavioral characteristics within this specific task. The…

This work aims at developing new methodologies to optimize computational costly complex systems (e.g., aeronautical engineering systems). The proposed surrogate-based method (often called Bayesian optimization) uses adaptive sampling to…

Like conventional software projects, projects in model-driven software engineering require adequate management of multiple versions of development artifacts, importantly allowing living with temporary inconsistencies. In the case of…

We present a novel approach, which is based on multiple-valued logic (MVL), to the verification and analysis of digital hardware designs, which extends the common ternary or quaternary approaches for simulations. The simulations which are…

Large pre-trained vision-language models (VLMs) offer a promising approach to leveraging human language for enhancing downstream tasks. However, VLMs such as CLIP face significant limitation: its performance is highly sensitive to prompt…

Evolving software is challenging, even more when it exists in many different variants. Such software evolves not only in time, but also in space--another dimension of complexity. While evolution in space is supported by a variety of…

Large Language Models (LLMs) have demonstrated impressive capabilities in code generation. While an interactive feedback loop can improve performance, writing effective tests is a non-trivial task. Early multi-agent frameworks, such as…

Although variational autoencoders (VAEs) represent a widely influential deep generative model, many aspects of the underlying energy function remain poorly understood. In particular, it is commonly believed that Gaussian encoder/decoder…

Variational Autoencoders (VAE) and their variants have been widely used in a variety of applications, such as dialog generation, image generation and disentangled representation learning. However, the existing VAE models have some…

Deep Learning (DL)-based methods have proven to be effective for software vulnerability detection, with a potential for substantial productivity enhancements for detecting vulnerabilities. Current methods mainly focus on detecting single…

Visual commonsense understanding requires Vision Language (VL) models to not only understand image and text but also cross-reference in-between to fully integrate and achieve comprehension of the visual scene described. Recently, various…

Evaluation in machine learning is usually informed by past choices, for example which datasets or metrics to use. This standardization enables the comparison on equal footing using leaderboards, but the evaluation choices become sub-optimal…