Related papers: Variable Name Recovery in Decompiled Binary Code u…
A recent trend in binary code analysis promotes the use of neural solutions based on instruction embedding models. An instruction embedding model is a neural network that transforms sequences of assembly instructions into embedding vectors.…
Self-attention based transformer models have been dominating many computer vision tasks in the past few years. Their superb model qualities heavily depend on the excessively large labeled image datasets. In order to reduce the reliance on…
Researchers have investigated the potential of leveraging pre-trained language models, such as CodeBERT, to enhance source code-related tasks. Previous methodologies have relied on CodeBERT's '[CLS]' token as the embedding representation of…
Due to increased access to clinical trial outcomes and analysis, researchers and scientists are able to iterate or improve upon relevant approaches more effectively. However, the metrics and related results of clinical trials typically do…
The cross-lingual language models are typically pretrained with masked language modeling on multilingual text or parallel sentences. In this paper, we introduce denoising word alignment as a new cross-lingual pre-training task.…
Third-Party Library (TPL) detection, which identifies reused libraries in binary code, is critical for software security analysis. At its core, TPL detection depends on binary decomposition-the process of partitioning a monolithic binary…
While (large) language models have significantly improved over the last years, they still struggle to sensibly process long sequences found, e.g., in books, due to the quadratic scaling of the underlying attention mechanism. To address…
Code retrieval, which retrieves code snippets based on users' natural language descriptions, is widely used by developers and plays a pivotal role in real-world software development. The advent of deep learning has shifted the retrieval…
Recently, masked video modeling has been widely explored and significantly improved the model's understanding ability of visual regions at a local level. However, existing methods usually adopt random masking and follow the same…
Active learning has been shown to be an effective way to alleviate some of the effort required in utilising large collections of unlabelled data for machine learning tasks without needing to fully label them. The representation mechanism…
We propose a novel semantic segmentation algorithm by learning a deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer net. The deconvolution network is composed of deconvolution and…
The dominant probing approaches rely on the zero-shot performance of image-text matching tasks to gain a finer-grained understanding of the representations learned by recent multimodal image-language transformer models. The evaluation is…
As pretrained models are increasingly shared on the web, ensuring that models can forget or delete sensitive, copyrighted, or private information upon request has become crucial. Machine unlearning has been proposed to address this…
A classic result of Lenstra [Math.~Oper.~Res.~1983] says that an integer linear program can be solved in fixed-parameter tractable (FPT) time for the parameter being the number of variables. We extend this result by incorporating…
Recurrent neural networks have proved to be an effective method for statistical language modeling. However, in practice their memory and run-time complexity are usually too large to be implemented in real-time offline mobile applications.…
Training models on low-resource named entity recognition tasks has been shown to be a challenge, especially in industrial applications where deploying updated models is a continuous effort and crucial for business operations. In such cases…
We propose an unsupervised hashing method which aims to produce binary codes that preserve the ranking induced by a real-valued representation. Such compact hash codes enable the complete elimination of real-valued feature storage and allow…
While invaluable for many computer vision applications, decomposing a natural image into intrinsic reflectance and shading layers represents a challenging, underdetermined inverse problem. As opposed to strict reliance on conventional…
State-of-the-art performance on language understanding tasks is now achieved with increasingly large networks; the current record holder has billions of parameters. Given a language model pre-trained on massive unlabeled text corpora, only…
We study machine learning formulations of inductive program synthesis; given input-output examples, we try to synthesize source code that maps inputs to corresponding outputs. Our aims are to develop new machine learning approaches based on…