Published in arXiv Preprint, 2025
We proposed a reinforcement learning tehchnique utilizing the Plackett-Luce distribution to find the optimal ordering of patches for long sequence vision transformers.
Recommended citation: Declan Kutscher, David M. Chan, Yutong Bai, Trevor Darrell, Ritwik Gupta. (2025). "REOrdering Patches Improves Vision Models." arXiv Preprint.
Download Paper
Published in AAAI Conf on Artificial Intelligence, Special Track on Social Impact, 2025
This work introduces a novel graph neural networks (GNNs)-based method to predict stream water temperature and reduce model bias across locations of different income and education levels.
Recommended citation: Erhu He, Declan Kutscher, Yiqun Xie, Jacob Zwart, Zhe Jiang, Huaxiu Yao, Xiaowei Jia. (2024). "Physics-Guided Fair Graph Sampling for Water Temperature Prediction in River Networks." AAAI Conf on Artificial Intelligence, Special Track on Social Impact..
Download Paper
Published in Carnegie Mellon University, Software Engineering Institutes Digital Library, 2024
In this paper, we investigate the usefulness and design methodology of applying large language models (LLMs) to improve and automate the process of coding case data. We introduce tools to guide LLMs to assist in this coding process.
Recommended citation: D. Kutscher, A. Whisnant, "Leveraging LLMs for Data Coding," Carnegie Mellon University, Software Engineering Institutes Digital Library. Software Engineering Institute, White Paper, 04-Nov-2024
Download Paper