papers

Publications (20)

cs.LG2024

Large Language Models Can Self-Improve At Web Agent Tasks

Ajay Patel, Markus Hofmarcher, Claudiu Leoveanu-Condrei +3

Training models to act as agents that can effectively navigate and perform actions in a complex environment, such as a web browser, has typically been challenging due to lack of tr…

cs.CL2024

DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows

Ajay Patel, Colin Raffel, Chris Callison-Burch

Large language models (LLMs) have become a dominant and important tool for NLP researchers in a wide range of tasks. Today, many researchers use LLMs in synthetic data generation,…

cs.CL2024

TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings

Zachary Horvitz, Ajay Patel, Kanishk Singh +3

The goal of text style transfer is to transform the style of texts while preserving their original meaning, often with only a few examples of the target style. Existing style trans…

cs.CL2024

Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution

Milad Alshomary, Narutatsu Ri, Marianna Apidianaki +3

Recent state-of-the-art authorship attribution methods learn authorship representations of texts in a latent, non-interpretable space, hindering their usability in real-world appli…

physics.med-ph2013

Motionless Phase Stepping in X-Ray Phase Contrast Imaging with a Compact Source

Houxun Miao, Lei Chen, Eric E. Bennett +6

X-ray phase contrast imaging offers a way to visualize the internal structures of an object without the need to deposit any radiation, and thereby alleviate the main concern in x-r…

cs.CL2026

FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale

Ajay Patel, Colin Raffel, Chris Callison-Burch

Due to limited supervised training data, large language models (LLMs) are typically pre-trained via a self-supervised "predict the next word" objective on a vast amount of unstruct…