Research Papers

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Can We Trust Text Anymore? A New Watermark for AI

Dara Bahri|John Wieting|Dana Alon|Donald Metzler

Racing Thoughts: Why AI Can't Keep Up With Context

Michael A. Lepori|Michael Mozer|Asma Ghandeharioun

Can LLMs Teach Themselves to Reason?

Xiangyu Peng|Congying Xia|Xinyi Yang|Caiming Xiong|Chien-Sheng Wu|Chen Xing

Mind-Controlled Robots? How Brainwaves Could Command Humanoids

Yiqun Duan|Qiang Zhang|Jinzhao Zhou|Jingkai Sun|Xiaowei Jiang|Jiahang Cao|Jiaxu Wang|Yiqian Yang|Wen Zhao|Gang Han|Yijie Guo|Chin-Teng Lin

Coding With AI: How to Supercharge Research

Tonghe Zhuang|Zhicheng Lin

Can LLMs Plan? Putting OpenAI's "Strawberry" to the Test

Karthik Valmeekam|Kaya Stechly|Atharva Gundawar|Subbarao Kambhampati

How Hackers Could Poison Your AI Search Results

Collin Zhang|Tingwei Zhang|Vitaly Shmatikov

How Human Uncertainty Impacts AI Evaluation

Aparna Elangovan|Jongwoo Ko|Lei Xu|Mahsa Elyasi|Ling Liu|Sravan Bodapati|Dan Roth

Can AI Judge Code? Introducing CodeJudge

Weixi Tong|Tianyi Zhang

The first platform built for prompt engineering