38 citations · 56 across the 27 of their papers we have counts for
9 papers · 1 filter
Probabilistic Model Checking of Autoregressive Neural Sequence Models
Helge Spieker, Dennis Gross, Arnaud Gotlieb
Test-set accuracy is silent on two issues that matter when deploying autoregressive neural sequence models: how much probability mass the system under test (SUT) places on constrai…
Metamorphic Testing with the Rashomon Set: Explanation Faithfulness in Machine Learning
Helge Spieker, Jørn Eirik Betten, Arnaud Gotlieb
Multiple machine learning models can achieve near-equivalent predictive performance on the same task, yet provide divergent feature-based explanations. This is called the Rashomon…
Efficiently Ranking Software Variants with Minimal Benchmarks
Théo Matricon, Mathieu Acher, Helge Spieker +1
Benchmarking is a common practice in software engineering to assess the qualities and performance of software variants, coming from multiple competing systems or from configuration…
Metamorphic Testing of Multimodal Human Trajectory Prediction
Helge Spieker, Nadjib Lazaar, Arnaud Gotlieb +1
Context: Predicting human trajectories is crucial for the safety and reliability of autonomous systems, such as automated vehicles and mobile robots. However, rigorously testing th…
Reusable Test Suites for Reinforcement Learning
Jørn Eirik Betten, Quentin Mazouni, Dennis Gross +2
Reinforcement learning (RL) agents show great promise in solving sequential decision-making tasks. However, validating the reliability and performance of the agent policies' behavi…
Prompting for Performance: Exploring LLMs for Configuring Software
Helge Spieker, Théo Matricon, Nassim Belmecheri +7
Software systems usually provide numerous configuration options that can affect performance metrics such as execution time, memory usage, binary size, or bitrate. On the one hand,…
Policy Testing with MDPFuzz (Replicability Study)
Quentin Mazouni, Helge Spieker, Arnaud Gotlieb +1
In recent years, following tremendous achievements in Reinforcement Learning, a great deal of interest has been devoted to ML models for sequential decision-making. Together with t…
Evaluating Human Trajectory Prediction with Metamorphic Testing
Helge Spieker, Nassim Belmecheri, Arnaud Gotlieb +1
The prediction of human trajectories is important for planning in autonomous systems that act in the real world, e.g. automated driving or mobile robots. Human trajectory predictio…
Testing for Fault Diversity in Reinforcement Learning
Quentin Mazouni, Helge Spieker, Arnaud Gotlieb +1
Reinforcement Learning is the premier technique to approach sequential decision problems, including complex tasks such as driving cars and landing spacecraft. Among the software va…