I’ll be looking for summer research interns Ai2 at the Aristo team (Aristo Team at AI2). Along with broad topics mentioned below, I’ll be focusing on model tuning and specialization for agents and data-driven discovery, in the paradigm of automated and AI-assisted scientific

I'm in Miami for #EMNLP2024! Presenting posters at sessions 9 and 12. I'll also be presenting at the Future of Event Detection workshop on Friday. Please reach out if you want to chat about reasoning or multimodality! ☕️ I'm also looking for 2025 summer internships.

Also, check out Nathaniel Weir's poster (also session 9) on this project here to learn more about our work on decompositional entailment and reasoning :) arxiv.org/abs/2402.14798

I’m presenting my Microsoft internship work today at #EMNLP2024! I’ll be in Riverfront from 2-3:30. Come say hi and chat about structured document generation and evaluation! TLDR: We unify the generation and evaluation of templatic views of documents. aclanthology.org/2024.findings-…

🤖🧠 I'll be considering applications for postdocs & PhD students to start at Yale in Fall 2025! If you are interested in the intersection of linguistics, cognitive science, & AI, I encourage you to apply! Postdoc link: rtmccoy.com/prospective_po… PhD link: rtmccoy.com/prospective_st…

Congratulations to all Johns Hopkins University researchers participating in #NeurIPS2024! Check out all Johns Hopkins University accepted papers, tutorials, and workshops at ai.jhu.edu/news/johns-hop….

I'm looking for a student (MSc/PhD) who is interested in working on assessing the feasibility of scientific claims using simulations, to work with me at University of Arizona. Start date as early as January. Please get in touch if you're interested.

I’ll be presenting CoGEX today at # NeurIPS — stop by East Exhibit Hall at 4:30 to chat about code-based reasoning! Also, my team at AWS is seeking interns and full-time RS on similar topics (reasoning x agents x code), so reach out if interested!

🚨 New preprint on transparent, tree-adaptive grounded reasoning! We introduce Bonsai, a versatile reasoning system that generates interpretable, grounded, and uncertainty-aware reasoning traces while enabling state-of-the-art performance on text and video benchmarks.

I'm recruiting a PhD student in AI & Scientific Discovery (start August 2025), particularly where scientific discovery intersects with code generation. If interested, please e-mail your CV. I'll also be at NAACL organizing the AI & Scientific Discovery Workshop (AISD) & can chat

**Certified Mitigation of Worst-Case LLM Copyright Infringement** TL;DR: We propose BloomScrub a framework to certifiably remove long verbatim quotes to reduce the risk of copyright violations. Challenge: Most existing copyright mitigation techniques for LLMs address