相关论文: Neural architectures for resolving references in p…

Code completion, one of the most useful features in the Integrated Development Environments (IDEs), can accelerate software development by suggesting the libraries, APIs, and method names in real-time. Recent studies have shown that…

Large Language Models (LLMs) demonstrate exceptional reasoning abilities, enabling strong generalization across diverse tasks such as commonsense reasoning and instruction following. However, as LLMs scale, inference costs become…

The Transformer architecture is superior to RNN-based models in computational efficiency. Recently, GPT and BERT demonstrate the efficacy of Transformer models on various NLP tasks using pre-trained language models on large-scale corpora.…

Neural program embeddings have shown much promise recently for a variety of program analysis tasks, including program synthesis, program repair, fault localization, etc. However, most existing program embeddings are based on syntactic…

We address the problem of automatic decompilation, converting a program in low-level representation back to a higher-level human-readable programming language. The problem of decompilation is extremely important for security researchers.…

Effective decision-making in the real world depends on memory that is both stable and adaptive: environments change over time, and agents must retain relevant information over long horizons while also updating or overwriting outdated…

Due to the high computational demands executing a rigorous comparison between hyperparameter optimization (HPO) methods is often cumbersome. The goal of this paper is to facilitate a better empirical evaluation of HPO methods by providing…

Recent work has shown that recurrent neural networks (RNNs) can implicitly capture and exploit hierarchical information when trained to solve common natural language processing tasks such as language modeling (Linzen et al., 2016) and…

There exist many problem domains where the interpretability of neural network models is essential for deployment. Here we introduce a recurrent architecture composed of input-switched affine transformations - in other words an RNN without…

In recent years, deep learning techniques have been developed to improve the performance of program synthesis from input-output examples. Albeit its significant progress, the programs that can be synthesized by state-of-the-art approaches…

We present a reality check on large language models and inspect the promise of retrieval augmented language models in comparison. Such language models are semi-parametric, where models integrate model parameters and knowledge from external…

Hardware-Software Co-Design is a highly successful strategy for improving performance of domain-specific computing systems. We argue for the application of the same methodology to deep learning; specifically, we propose to extend neural…

A source code summary of a subroutine is a brief description of that subroutine. Summaries underpin a majority of documentation consumed by programmers, such as the method summaries in JavaDocs. Source code summarization is the task of…

Neural network architectures for image demosaicing have been become more and more complex. This results in long training periods of such deep networks and the size of the networks is huge. These two factors prevent practical implementation…

The remarkable progress in deep learning in recent years is largely driven by improvements in scale, where bigger models are trained on larger datasets for longer schedules. To predict the benefit of scale empirically, we argue for a more…

Recent advances in probabilistic modelling have led to a large number of simulation-based inference algorithms which do not require numerical evaluation of likelihoods. However, a public benchmark with appropriate performance metrics for…

Neural Architecture Search (NAS) benchmarks significantly improved the capability of developing and comparing NAS methods while at the same time drastically reduced the computational overhead by providing meta-information about thousands of…

There is mounting evidence that existing neural network models, in particular the very popular sequence-to-sequence architecture, struggle to systematically generalize to unseen compositions of seen components. We demonstrate that one of…

The reasoning abilities are one of the most enigmatic and captivating aspects of large language models (LLMs). Numerous studies are dedicated to exploring and expanding the boundaries of this reasoning capability. However, tasks that embody…

The ability to maintain and manipulate information over time is a fundamental aspect of living beings and Artificial Intelligence. While modern models have achieved remarkable success in tasks like natural language processing, evaluating…