相关论文: TorchProbe: Fuzzing Dynamic Deep Learning Compiler…

VIBETENSOR is an open-source research system software stack for deep learning, generated by LLM-powered coding agents under high-level human guidance. In this paper, "fully generated" refers to code provenance: implementation changes were…

Deep learning algorithms have made many breakthroughs and have various applications in real life. Computational resources become a bottleneck as the data and complexity of the deep learning pipeline increases. In this paper, we propose…

Evolutionary computation is an important component within various fields such as artificial intelligence research, reinforcement learning, robotics, industrial automation and/or optimization, engineering design, etc. Considering the…

Crafting high-quality fuzz drivers not only is time-consuming but also requires a deep understanding of the library. However, the state-of-the-art automatic fuzz driver generation techniques fall short of expectations. While fuzz drivers…

The article presents the torchosr package - a Python package compatible with PyTorch library - offering tools and methods dedicated to Open Set Recognition in Deep Neural Networks. The package offers two state-of-the-art methods in the…

Vulnerable software represents a tremendous threat to modern information systems. Vulnerabilities in widespread applications may be used to spread malware, steal money and conduct target attacks. To address this problem, developers and…

Kotlin is a relatively new programming language from JetBrains: its development started in 2010 with release 1.0 done in early 2016. The Kotlin compiler, while slowly and steadily becoming more and more mature, still crashes from time to…

Solving complex computer vision tasks by deep learning techniques relies on large amounts of (supervised) image data, typically unavailable in industrial environments. The lack of training data starts to impede the successful transfer of…

The joint task of bug localization and program repair is an integral part of the software development process. In this work we present DeepDebug, an approach to automated debugging using large, pretrained transformers. We begin by training…

The goal of hyperparameter tuning (or hyperparameter optimization) is to optimize the hyperparameters to improve the performance of the machine or deep learning model. spotPython (``Sequential Parameter Optimization Toolbox in Python'') is…

In this paper, we introduce MCTensor, a library based on PyTorch for providing general-purpose and high-precision arithmetic for DL training. MCTensor is used in the same way as PyTorch Tensor: we implement multiple basic, matrix-level…

Mutation testing is an effective technique for assessing the effectiveness of test suites by systematically injecting artificial faults into programs. However, existing mutation testing techniques fall short in capturing many types of…

DeepLog is an operational neurosymbolic framework that unifies logic and deep learning within standard PyTorch workflows. While existing neurosymbolic systems focus on a particular paradigm and semantics, DeepLog serves as a universal…

We present PyTorch Geometric Temporal a deep learning framework combining state-of-the-art machine learning algorithms for neural spatiotemporal signal processing. The main goal of the library is to make temporal geometric deep learning…

Speech deepfake detection is a well-established research field with different models, datasets, and training strategies. However, the lack of standardized implementations and evaluation protocols limits reproducibility, benchmarking, and…

Deep Learning (DL) libraries like TensorFlow and Pytorch simplify machine learning (ML) model development but are prone to bugs due to their complex design. Bug-finding techniques exist, but without precise API specifications, they produce…

The development of model compression is continuously motivated by the evolution of various neural network accelerators with ASIC or FPGA. On the algorithm side, the ultimate goal of quantization or pruning is accelerating the expensive DNN…

Modern LLMs typically require multistage training pipelines to achieve strong downstream performance, with post-training serving as the main interface for adapting open-weight models. We introduce torchtune, a PyTorch-native library…

When engineers train deep learning models, they are very much 'flying blind'. Commonly used methods for real-time training diagnostics, such as monitoring the train/test loss, are limited. Assessing a network's training process solely…

Deep learning has enabled major advances in the fields of computer vision, natural language processing, and multimedia among many others. Developing a deep learning system is arduous and complex, as it involves constructing neural network…