no code implementations • 29 Nov 2023 • Liya Wang, Jason Chou, Xin Zhou, Alex Tien, Diane M Baumgartner
The advent of ChatGPT and GPT-4 has captivated the world with large language models (LLMs), demonstrating exceptional performance in question-answering, summarization, and content generation.
no code implementations • 16 May 2023 • Liya Wang, Jason Chou, Dave Rouck, Alex Tien, Diane M Baumgartner
Learning effective sentence representations is crucial for many Natural Language Processing (NLP) tasks, including semantic search, semantic textual similarity (STS), and clustering.
no code implementations • 28 Feb 2023 • Liya Wang, Alex Tien
As Masked Image Modeling (MIM), a self-supervised learning (SSL) technique, has been shown as a better way for learning visual feature representation, it presents a new opportunity for improving ML performance on the scene classification task.
no code implementations • 28 Jan 2023 • Liya Wang, Alex Tien
Our results show that ViTDet can consistently outperform its convolutional neural network counterparts on horizontal bounding box (HBB) object detection by a large margin (up to 17% on average precision) and that it achieves the competitive performance for oriented bounding box (OBB) object detection.
no code implementations • 17 Nov 2021 • Erik Vargo, Alex Tien, Arian Jafari
This paper proposes a novel approach to predict and determine whether the average taxi- out time at an airport will exceed a pre-defined threshold within the next hour of operations.
no code implementations • 4 Nov 2021 • Liya Wang, Alex Tien, Jason Chou
Traffic, demand, weather, and traffic management actions are all critical inputs to any prediction model.