Related papers: Deep Data Flow Analysis

Many recent machine learning models rely on fine-grained dynamic control flow for training and inference. In particular, models based on recurrent neural networks and on reinforcement learning depend on recurrence relations, data-dependent…

Automated Machine Learning with ensembling (or AutoML with ensembling) seeks to automatically build ensembles of Deep Neural Networks (DNNs) to achieve qualitative predictions. Ensemble of DNNs are well known to avoid over-fitting but they…

DL compiler's primary function is to translate DNN programs written in high-level DL frameworks such as PyTorch and TensorFlow into portable executables. These executables can then be flexibly executed by the deployed host programs.…

Large Language Models (LLMs) have significantly advanced code analysis tasks, yet they struggle to detect malicious behaviors fragmented across files, whose intricate dependencies easily get lost in the vast amount of benign code. We…

The rapid growth of interest in large language models (LLMs) reflects their potential for flexibility and generalization, and attracted the attention of a diverse range of researchers. However, the advent of these techniques has also…

Large language models (LLMs) and transformer-based architectures are increasingly utilized for source code analysis. As software systems grow in complexity, integrating LLMs into code analysis workflows becomes essential for enhancing…

Conversational machine comprehension (MC) has proven significantly more challenging compared to traditional MC since it requires better utilization of conversation history. However, most existing approaches do not effectively capture…

Deep learning models with convolutional and recurrent networks are now ubiquitous and analyze massive amounts of audio, image, video, text and graph data, with applications in automatic translation, speech-to-text, scene understanding,…

Automated Machine Learning (AutoML) has been used successfully in settings where the learning task is assumed to be static. In many real-world scenarios, however, the data distribution will evolve over time, and it is yet to be shown…

Manufacturing planners face complex operational challenges that require seamless collaboration between human expertise and intelligent systems to achieve optimal performance in modern production environments. Traditional approaches to…

Apart from forming the backbone of compiler optimization, static dataflow analysis has been widely applied in a vast variety of applications, such as bug detection, privacy analysis, program comprehension, etc. Despite its importance,…

Traditional software engineering programming paradigms are mostly object or procedure oriented, driven by deterministic algorithms. With the advent of deep learning and cognitive sciences there is an emerging trend for data-driven…

Recent advances in Large Language Models (LLMs) have shown promise in function-level code generation, yet repository-level software engineering tasks remain challenging. Current solutions predominantly rely on proprietary LLM agents, which…

Over the past decade, extensive research efforts have been dedicated to the extraction of information from textual process descriptions. Despite the remarkable progress witnessed in natural language processing (NLP), information extraction…

Language models have become increasingly powerful tools for formal mathematical reasoning. However, most existing approaches rely exclusively on either large general-purpose models or smaller specialized models, each with distinct…

In this paper, we present our vision of differentiable ML pipelines called DiffML to automate the construction of ML pipelines in an end-to-end fashion. The idea is that DiffML allows to jointly train not just the ML model itself but also…

In this work, which is done in the context of a (moded) logic programming language, we devise a data-flow analysis dedicated to computing what we call argument profiles. Such a profile essentially describes, for each argument of a…

Optimizing a machine learning pipeline for a task at hand requires careful configuration of various hyperparameters, typically supported by an AutoML system that optimizes the hyperparameters for the given training dataset. Yet, depending…

Using Large Language Models (LLMs) to process graph-structured data is an active research area, yet current state-of-the-art approaches typically rely on multi-step pipelines with Graph Neural Network (GNN) encoders that compress rich…

C is the lingua franca of programming and almost any device can be programmed using C. However, programming mod-ern heterogeneous architectures such as multi-core CPUs and GPUs requires explicitly expressing parallelism as well as…