Related papers: Static Analysis Driven Enhancements for Comprehens…

The dominant retrieve-then-rank pipeline in large-scale recommender systems suffers from mis-calibration and engineering overhead due to its architectural split and differing optimization objectives. While recent generative sequence models…

This paper introduces a simple JavaScript-based web application designed to assist educators in detecting AI-generated content in student essays and written assignments. Unlike existing AI detection tools that rely on obfuscated machine…

We study the feasibility of a Data Science assistant powered by a sequence-to-sequence transformer by training a new model JuPyT5 on all publicly available Jupyter Notebook GitHub repositories and developing a new metric: Data Science…

In the last decade, an impressive increase in software adaptions has led to a surge in log data production, making manual log analysis impractical and establishing the necessity for automated methods. Conversely, most automated analysis…

One of the primary obstacles in the advancement of Natural Language Processing (NLP) technologies for low-resource languages is the lack of annotated datasets for training and testing machine learning models. In this paper, we present…

Language Models (LLMs), such as transformer-based neural networks trained on billions of parameters, have become increasingly prevalent in software engineering (SE). These models, trained on extensive datasets that include code…

Recent studies have extensively explored NPU architectures for accelerating AI inference in on-device environments, which are inherently resource-constrained. Meanwhile, transformer-based large language models (LLMs) have become dominant,…

Jupyter notebooks allow to bundle executable code with its documentation and output in one interactive environment, and they represent a popular mechanism to document and share computational workflows, including for research publications.…

Data collection from manual labeling provides domain-specific and task-aligned supervision for data-driven approaches, and a critical mass of well-annotated resources is required to achieve reasonable performance in natural language…

Due to the rise of machine learning, Python is an increasingly popular programming language. Python, however, is dynamically typed. Dynamic typing has shown to have drawbacks when a project grows, while at the same time it improves…

With the rapid development of large language models (LLMs), their application to cell type annotation has drawn increasing attention. However, general-purpose LLMs often face limitations in this specific task due to the lack of guidance…

Type annotations in Python enhance maintainability and error detection. However, generating these annotations manually is error prone and requires extra effort. Traditional automation approaches like static analysis, machine learning, and…

Large-scale datasets are essential to modern day deep learning. Advocates argue that understanding these methods requires dataset transparency (e.g. "dataset curation, motivation, composition, collection process, etc..."). However, almost…

Synthetic data offers a scalable solution for vision-language pre-training, yet current state-of-the-art methods typically rely on scaling up a single generative backbone, which introduces generator-specific spectral biases and limits…

Manually labeling datasets with object masks is extremely time consuming. In this work, we follow the idea of Polygon-RNN to produce polygonal annotations of objects interactively using humans-in-the-loop. We introduce several important…

The autonomous synthesis of deep research reports represents a critical frontier for Large Language Models (LLMs), demanding sophisticated information orchestration and non-linear narrative logic. Current approaches rely on rigid predefined…

In this work, we investigate several neural network architectures for fine-grained entity type classification. Particularly, we consider extensions to a recently proposed attentive neural architecture and make three key contributions.…

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop…

The advent of recurrent neural networks for handwriting recognition marked an important milestone reaching impressive recognition accuracies despite the great variability that we observe across different writing styles. Sequential…

Fine-tuning for large language models (LLMs) typically requires substantial amounts of high-quality supervised data, which is both costly and labor-intensive to acquire. While synthetic data generation has emerged as a promising solution,…