Related papers: Context-Specific Instruction: A Longitudinal Study…
In large programming classes, it takes a significant effort from teachers to evaluate exercises and provide detailed feedback. In systems programming, test cases are not sufficient to assess exercises, since concurrency and resource…
Context: Fault localization (FL) is the key activity while debugging a program. Any improvement to this activity leads to significant improvement in total software development cost. There is an internal linkage between the program spectrum…
Transformer-based large language models exhibit in-context learning, enabling adaptation to downstream tasks via few-shot prompting with demonstrations. In practice, such models are often fine-tuned to improve zero-shot performance on…
In today's data-driven era, deep learning is vital for processing massive datasets, yet single-device training is constrained by computational and memory limits. Distributed deep learning overcomes these challenges by leveraging multiple…
The automated program repair field has attracted substantial interest over the years, but despite significant research efforts, creating a system that works well for complex semantic bugs such as security vulnerabilities has proven…
In-context learning is a surprising and important phenomenon that emerged when modern language models were scaled to billions of learned parameters. Without modifying a large language model's weights, it can be tuned to perform various…
GPT-3 can perform numerous tasks when provided a natural language prompt that contains a few training examples. We show that this type of few-shot learning can be unstable: the choice of prompt format, training examples, and even the order…
Contextualizing problems to align with student interests can significantly improve learning outcomes. However, this task often presents scalability challenges due to resource and time constraints. Recent advancements in Large Language…
Modern Security Operations Centres (SOCs) integrate diverse tools, such as SIEM, IDS, and XDR systems, offering rich contextual data, including alert enrichments, flow features, and similar case histories. Yet, analysts must still manually…
Adaptive learning technologies increasingly rely on real time physiological analytics to trigger instructional support automatically yet how system driven decisions interact with learners ongoing problem solving processes remains poorly…
Traditional end-to-end (E2E) training of deep networks necessitates storing intermediate activations for back-propagation, resulting in a large memory footprint on GPUs and restricted model parallelization. As an alternative, greedy local…
A key human ability is to decompose a scene into distinct objects and use their relationships to understand the environment. Object-centric learning aims to mimic this process in an unsupervised manner. Recently, the slot attention-based…
Tangled code changes, commits that conflate unrelated modifications such as bug fixes, refactorings, and enhancements, introduce significant noise into bug datasets and adversely affect the performance of bug prediction models. Addressing…
Position-controlled evaluation is standard for retrieval tasks such as Needle-in-a-Haystack and RULER, but mainstream reasoning benchmarks do not control positional placement of target tasks in long contexts. We audit 11 long-context…
This paper presents a large-scale study that investigates the bug resolution characteristics among popular Github projects written in different programming languages. We explore correlations but, of course, we cannot infer causation.…
Contextual bandits are a common problem faced by machine learning practitioners in domains as diverse as hypothesis testing to product recommendations. There have been a lot of approaches in exploiting rich data representations for…
Instructors have limited time and resources to help struggling students, and these resources should be directed to the students who most need them. To address this, researchers have constructed models that can predict students' final course…
High quality bugs are key to training the next generation of language model based software engineering (SWE) agents. We introduce a novel method for synthetic generation of difficult and diverse bugs. Our method instructs SWE Agents to…
Monocular depth estimation and semantic segmentation are two fundamental goals of scene understanding. Due to the advantages of task interaction, many works study the joint task learning algorithm. However, most existing methods fail to…
Neural processes (NPs) aim to stochastically complete unseen data points based on a given context dataset. NPs essentially leverage a given dataset as a context representation to derive a suitable identifier for a novel task. To improve the…