Related papers: ast2vec: Utilizing Recursive Neural Encodings of P…
Recent research has achieved impressive results on understanding and improving source code by building up on machine-learning techniques developed for natural languages. A significant advancement in natural-language understanding has come…
The ability to execute code is a prerequisite for various dynamic program analyses. Learning-guided execution has been proposed as an approach to enable the execution of arbitrary code snippets by letting a neural model predict likely…
Learning neural program embeddings is key to utilizing deep neural networks in program languages research --- precise and efficient program representations enable the application of deep models to a wide range of program analysis tasks.…
Recently there have been many advances in research on language modeling of source code. Applications range from code suggestion and completion to code summarization. However, complete program synthesis of industry-grade programming…
The diverse nature of protein prediction tasks has traditionally necessitated specialized models, hindering the development of broadly applicable and computationally efficient Protein Language Models (PLMs). In this work, we introduce…
Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax networks, a modeling framework for these problems. The outputs…
A code generation system generates programming language code based on an input natural language description. State-of-the-art approaches rely on neural networks for code generation. However, these code generators suffer from two problems.…
Dynamic regression trees are an attractive option for automatic regression and classification with complicated response surfaces in on-line application settings. We create a sequential tree model whose state changes in time with the…
Large Language Models (LLMs) for code are a family of high-parameter, transformer-based neural networks pre-trained on massive datasets of both natural and programming languages. These models are rapidly being employed in commercial…
Dense retrieval calls for discriminative embeddings to represent the semantic relationship between query and document. It may benefit from the using of large language models (LLMs), given LLMs' strong capability on semantic understanding.…
While deep neural networks have demonstrated remarkable performance across various tasks, they typically require massive training data. Due to the presence of redundancies and biases in real-world datasets, not all data in the training…
We used Data Maps to model and characterize the AuTexTification dataset. This provides insights about the behaviour of individual samples during training across epochs (training dynamics). We characterized the samples across 3 dimensions:…
A practical approach to activate long chain-of-thoughts reasoning ability in pre-trained large language models is to perform supervised fine-tuning on instruction datasets synthesized by strong Large Reasoning Models such as DeepSeek-R1,…
Recent years have seen the successful application of large pre-trained models to code representation learning, resulting in substantial improvements on many code-related downstream tasks. But there are issues surrounding their application…
Accelerating model convergence in resource-constrained environments is essential for fast and efficient neural network training. This work presents learn2mix, a new training strategy that adaptively adjusts class proportions within batches,…
Adverse drug events (ADE) are prevalent and costly. Clinical trials are constrained in their ability to identify potential ADEs, motivating the development of spontaneous reporting systems for post-market surveillance. Statistical methods…
Word-vector representations associate a high dimensional real-vector to every word from a corpus. Recently, neural-network based methods have been proposed for learning this representation from large corpora. This type of word-to-vector…
Detecting parallelizable code regions is a challenging task, even for experienced developers. Numerous recent studies have explored the use of machine learning for code analysis and program synthesis, including parallelization, in light of…
In the age of big data and machine learning, at a time when the techniques and methods of software development are evolving rapidly, a problem has arisen: programmers can no longer detect all the security flaws and vulnerabilities in their…
Citation sentiment analysis is an important task in scientific paper analysis. Existing machine learning techniques for citation sentiment analysis are focusing on labor-intensive feature engineering, which requires large annotated corpus.…