Research Papers

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Catching AI Misbehavior: A New Approach

Mengdi Zhang|Kai Kiat Goh|Peixin Zhang|Jun Sun

Supercharging Bug Fixes with AI-Powered Search

Thanh Le-Cong|Bach Le|Toby Murray

Can AI Predict Molecular Binding?

Janghoon Ock|Tirtha Vinchurkar|Yayati Jadhav|Amir Barati Farimani

Can AI Detectors Spot Machine-Written Text?

Ram Mohan Rao Kadiyala

AI Eye Exams: How VQA Transforms Eye Care

Xiaolan Chen|Ruoyu Chen|Pusheng Xu|Weiyi Zhang|Xianwen Shang|Mingguang He|Danli Shi

Making AI Safer: A New Approach to Content Moderation

Jing-Jing Li|Valentina Pyatkin|Max Kleiman-Weiner|Liwei Jiang|Nouha Dziri|Anne G. E. Collins|Jana Schaich Borg|Maarten Sap|Yejin Choi|Sydney Levine

Balancing Act: LLMs, Fairness, and Privacy

Chen Qian|Dongrui Liu|Jie Zhang|Yong Liu|Jing Shao

Can LLMs Really Reason About Cause and Effect?

Longxuan Yu|Delin Chen|Siheng Xiong|Qingyang Wu|Qingzhen Liu|Dawei Li|Zhikai Chen|Xiaoze Liu|Liangming Pan

Taming the Beast: Stabilizing LLM Training

Oleg Rybakov|Mike Chrzanowski|Peter Dykas|Jinze Xue|Ben Lanir

The first platform built for prompt engineering