Related papers: CUPID: Leveraging ChatGPT for More Accurate Duplic…
Despite their wide adoption in various domains (e.g., healthcare, finance, software engineering), Deep Learning (DL)-based applications suffer from many bugs, failures, and vulnerabilities. Reproducing these bugs is essential for their…
Automated debugging techniques have the potential to reduce developer effort in debugging, and have matured enough to be adopted by industry. However, one critical issue with existing techniques is that, while developers want rationales for…
In Deepfake Detection (DFD) tasks, researchers proposed two types of MLLM-based methods: complementary combination with small DFD detectors, or static forgery knowledge injection. The lack of professional forgery knowledge hinders the…
Debugging CUDA programs has long been challenging because failures often arise from subtle interactions among hardware behavior, compiler decisions, memory hierarchy, and asynchronous execution. More importantly, with the rapid expansion of…
With the growing ubiquity of multi-core architectures, concurrent systems have become essential but increasingly prone to complex issues such as data races and deadlocks. While modern issue-tracking systems facilitate the reporting of such…
Deep Learning (DL) library bugs affect downstream DL applications, emphasizing the need for reliable systems. Generating valid input programs for fuzzing DL libraries is challenging due to the need for satisfying both language…
Continuous cloud service performance benchmarking is essential for detecting performance bugs early before deploying them to production. However, detecting performance regressions using application benchmarks, which usually treat the system…
Context: Deep learning has achieved remarkable progress in various domains. However, like any software system, deep learning systems contain bugs, some of which can have severe impacts, as evidenced by crashes involving autonomous vehicles.…
Bug reports provide critical insights into software quality, yet existing datasets often suffer from limited scope, outdated content, or insufficient metadata for machine learning. To address these limitations, we present GitBugs-a…
Efficient CUDA implementations of attention mechanisms are critical to modern deep learning systems, yet supporting diverse and evolving attention variants remains challenging. Existing frameworks and compilers trade performance for…
With the rapid advancement of Artificial Intelligence, particularly in Natural Language Processing, Large Language Models (LLMs) have become pivotal in educational question-answering systems, especially university admission chatbots.…
Bug fixing holds significant importance in software development and maintenance. Recent research has made substantial strides in exploring the potential of large language models (LLMs) for automatically resolving software bugs. However, a…
Automated crash reporting systems generate large volumes of duplicate reports, overwhelming issue-tracking systems and increasing developer workload. Traditional stack trace-based deduplication methods, relying on string similarity,…
Bitmap indexes are widely used for read-intensive analytical workloads because they are clustered and offer efficient reads with a small memory footprint. However, they are notoriously inefficient to update. As analytical applications are…
Deepfake techniques generate highly realistic data, making it challenging for humans to discern between actual and artificially generated images. Recent advancements in deep learning-based deepfake detection methods, particularly with…
Random testing has proven to be an effective technique for compiler validation. However, the debugging of bugs identified through random testing presents a significant challenge due to the frequent occurrence of duplicate test programs that…
Assessing the correctness of distributed and parallel applications is notoriously difficult due to the complexity of the concurrent behaviors and the difficulty to reproduce bugs. In this context, Dynamic Partial Order Reduction (DPOR)…
Personalization of Large Language Models (LLMs) often assumes users hold static preferences that reflect globally in all tasks. In reality, humans hold dynamic preferences that change depending on the context. As users interact with an LLM…
As software systems grow increasingly complex, ensuring security during development poses significant challenges. Traditional manual code audits are often expensive, time-intensive, and ill-suited for fast-paced workflows, while automated…
Debugging is a critical but challenging task for programmers. This paper proposes ChatDBG, an AI-powered debugging assistant. ChatDBG integrates large language models (LLMs) to significantly enhance the capabilities and user-friendliness of…