Related papers: Towards a Complete Metamorphic Testing Pipeline
Operations Research (OR) relies on expert-driven modeling-a slow and fragile process ill-suited to novel scenarios. While large language models (LLMs) can automatically translate natural language into optimization models, existing…
Commit message generation (CMG) is a challenging task in automated software engineering that aims to generate natural language descriptions of code changes for commits. Previous methods all start from the modified code snippets, outputting…
Machine translation has wide applications in daily life. In mission-critical applications such as translating official documents, incorrect translation can have unpleasant or sometimes catastrophic consequences. This motivates recent…
In this paper, we address the problem of reference tracking for uncertain nonlinear systems. Since collecting data from the target system (i.e., the system of interest) is often challenging, our objective is to design optimal controllers…
Round-trip Machine Translation (MT) is a popular choice for paraphrase generation, which leverages readily available parallel corpora for supervision. In this paper, we formalize the implicit similarity function induced by this approach,…
A metamorphic robotic system is an aggregate of homogeneous robot units which can individually and selectively locomote in such a way as to change the global shape of the system. We introduce a mathematical framework for defining and…
This paper evaluates the use of metamorphic relations to enhance the robustness and real-world performance of machine learning models. We propose a Metamorphic Retraining Framework, which applies metamorphic relations to data and utilizes…
Fault analysis and resolution of faults should be part of any end-to-end system development process. This paper is concerned with developing a formal transformation method that maps control flows modeled in UML Activities to semantically…
The development and identification of effective optimization algorithms for non-convex real-world problems is a challenge in global optimization. Because theoretical performance analysis is difficult, and problems based on models of…
Identifying the main contributions related to the Automated Test Production (ATP) of Computer Programs and providing an overview about models, methodologies and tools used for this purpose is the aim of this Systematic Literature Review…
Machine translation (MT) is an area of study in Natural Language processing which deals with the automatic translation of human language, from one language to another by the computer. Having a rich research history spanning nearly three…
This thesis focuses on improving the pre-training of natural language models using unsupervised raw data to make them more efficient and aligned with downstream applications. In the first part, we introduce three alternative pre-training…
Meta-learning is a branch of machine learning which aims to synthesize data from a distribution of related tasks to efficiently solve new ones. In process control, many systems have similar and well-understood dynamics, which suggests it is…
Large sequence model (SM) such as GPT series and BERT has displayed outstanding performance and generalization capabilities on vision, language, and recently reinforcement learning tasks. A natural follow-up question is how to abstract…
The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. Recent advancements approach this through sequence modeling,…
Confluence of a nondeterministic program ensures a functional input-output relation, freeing the programmer from considering the actual scheduling strategy, and allowing optimized and perhaps parallel implementations. The more general…
We propose Dynamic Meta-Metrics (DMM), a framework for machine translation evaluation that learns source-sentence conditioned combinations of existing metrics. Rather than relying on a single static ensemble or language-specific weighting,…
Machine learning models are often brittle on production data despite achieving high accuracy on benchmark datasets. Benchmark datasets have traditionally served dual purposes: first, benchmarks offer a standard on which machine learning…
Transformation Synchronization is the problem of recovering absolute transformations from a given set of pairwise relative motions. Despite its usefulness, the problem remains challenging due to the influences from noisy and outlier…
Generating text from structured data is challenging because it requires bridging the gap between (i) structure and natural language (NL) and (ii) semantically underspecified input and fully specified NL output. Multilingual generation…