A.I. Researcher focused on, Neuro-symbolic Reasoning, Commonsense, and Deep RL
Hi! I am a Ph.D. student advised by Greg Durrett at the University of Texas in Austin.
My passion is in researching and developing language systems capable of reasoning on real-world problems.
My work spans Natural Language Reasoning, Neuro-Symbolic systems, Commonsense, and modeling interactions with Deep Reinforcement Learning.
Publications
Zayne Sprague, Fangcong Yin, Juan Diego Rodriguez, Dongwei Jiang, Manya Wadhwa, Prasann Singhal, Xinyu Zhao, Xi Ye, Kyle Mahowald, Greg Durrett. 2024, To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning. Preprint
Zayne Sprague, Xi Ye, Kaj Bostrom, Swarat Chaudhuri, and Greg Durrett. 2024, MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning. Proceedings of the Twelfth International Conference on Learning Representations (ICLR 2024) As a Spotlight Presentation
Zayne Sprague, Kaj Bostrom, Swarat Chaudhuri, and Greg Durrett. 2023, Deductive Additivity for Planning of Natural Language Proofs. Natural Language Reasoning and Structured Explanations Workshop at ACL
Zayne Sprague*, Rohan Chandra*, Joydeep Biswas. 2023, SOCIALGYM 2.0: Simulator for Multi-Agent Social Robot Navigation in Shared Human Spaces. Demo at Association for the Advancement of Artificial Intelligence (AAAI).
Zayne Sprague, Kaj Bostrom, Swarat Chaudhuri, and Greg Durrett. 2022, Natural Language Deduction with Incomplete Information. Proceedings of the Conference on Empirical Methods for Natural Language Processing (EMNLP).
Kaj Bostrom, Zayne Sprague, Swarat Chaudhuri, and Greg Durrett. 2022. Natural Language Natural Language Deduction through Search over Statement Compositions Findings of the Conference on Empirical Methods for Natural Language Processing (EMNLP).
Links
Taur Lab: NLP Lab
UT AMRL: Robotics Lab
UT NLP Site: UT’s site for all NLP research groups
School Email: zaynesprague@utexas.edu
Personal Email: zaynesprague@gmail.com