Related papers: Ahead of Time Mutation Based Fault Localisation us…

While most ML models expect independent and identically distributed data, this assumption is often violated in real-world scenarios due to distribution shifts, resulting in the degradation of machine learning model performance. Until now,…

Debugging is one of the most time-consuming and expensive tasks in software development and circuit design. Several formula-based fault localisation (FBFL) methods have been proposed, but they fail to guarantee a set of diagnoses across all…

In recent years, several probabilistic techniques have been applied to various debugging problems. However, most existing probabilistic debugging systems use relatively simple statistical models, and fail to generalize across multiple…

Supervised fine-tuning (SFT) is a standard approach to adapting large language models (LLMs) to new domains. In this work, we improve the statistical efficiency of SFT by selecting an informative subset of training examples. Specifically,…

In machine learning, the cost function is crucial because it measures how good or bad a system is. In image classification, well-known networks only consider modifying the network structures and applying cross-entropy loss at the end of the…

Code Large Language Models (CLLMs) have exhibited outstanding performance in program synthesis, attracting the focus of the research community. The evaluation of CLLM's program synthesis capability has generally relied on manually curated…

Deep Learning (DL) applications are being used to solve problems in critical domains (e.g., autonomous driving or medical diagnosis systems). Thus, developers need to debug their systems to ensure that the expected behavior is delivered.…

This paper introduces a novel perspective about error in machine learning and proposes inverse feature learning (IFL) as a representation learning approach that learns a set of high-level features based on the representation of error for…

Active multi-fidelity surrogate modeling is developed for multi-condition airfoil shape optimization to reduce high-fidelity CFD cost while retaining RANS-level accuracy. The framework couples a low-fidelity-informed Gaussian process…

LLMs are rapidly being adopted to build powerful tools and agents for software engineering, but most of them rely heavily on extremely large closed-source models. This, in turn, can hinder wider adoption due to security issues as well as…

This work aims to tackle Model Inversion (MI) attack on Split Federated Learning (SFL). SFL is a recent distributed training scheme where multiple clients send intermediate activations (i.e., feature map), instead of raw data, to a central…

Mutation testing may be used to guide test case generation and as a technique to assess the quality of test suites. Despite being used frequently, mutation testing is not so commonly applied in the mobile world. One critical challenge in…

We consider Decision-Focused Federated Learning (DFFL), a predict-then-optimize setting in which multiple clients collaboratively train predictive models for downstream linear optimization problems without exchanging raw data. Besides the…

At submicron manufacturing technology nodes process variations affect circuit performance significantly. This trend leads to a large timing margin and thus overdesign to maintain yield. To combat this pessimism, post-silicon clock tuning…

Static analysis tools are frequently used to detect potential vulnerabilities in software systems. However, an inevitable problem of these tools is their large number of warnings with a high false positive rate, which consumes time and…

Precise estimation of downstream performance in large language models (LLMs) prior to training is essential for guiding their development process. Scaling laws analysis utilizes the statistics of a series of significantly smaller sampling…

Software failures remain a major challenge in modern software development, and identifying the code elements responsible for failures is a time-consuming debugging task. While extensive research has focused on fault localization in the…

With the increasing release of powerful language models trained on large code corpus (e.g. CodeBERT was trained on 6.4 million programs), a new family of mutation testing tools has arisen with the promise to generate more "natural" mutants…

Recent efforts in fine-tuning language models often rely on automatic data selection, commonly using Nearest Neighbors retrieval from large datasets. However, we theoretically show that this approach tends to select redundant data, limiting…

High-impedance arc faults (HIAFs) in medium-voltage electrical distribution systems are difficult to detect due to their low fault current levels and nonlinear transient behavior. Traditional detection algorithms generally struggle with…