Research Papers

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

How LLMs Learn in Context: Unpacking the Mystery of In-Context Learning

Jiaoda Li|Yifan Hou|Mrinmaya Sachan|Ryan Cotterell

Can AI Catch Hidden Messages? New Steganalysis Research

Yifan Tang|Yihao Wang|Ru Zhang|Jianyi Liu

Unlocking the Secrets of Multi-Modal AI: How Images and Text Combine in Large Language Models

Samyadeep Basu|Martin Grayson|Cecily Morrison|Besmira Nushi|Soheil Feizi|Daniela Massiceti

Is Your AI Cheating on Benchmarks? The Truth About Data Contamination

Cheng Xu|Shuhao Guan|Derek Greene|M-Tahar Kechadi

Why Transformers Need Glasses: Information Loss in LLMs

Federico Barbero|Andrea Banino|Steven Kapturowski|Dharshan Kumaran|João G. M. Araújo|Alex Vitvitskyi|Razvan Pascanu|Petar Veličković

Unlocking AI Reasoning: The Power of a 'Buffer of Thoughts'

Ling Yang|Zhaochen Yu|Tianjun Zhang|Shiyi Cao|Minkai Xu|Wentao Zhang|Joseph E. Gonzalez|Bin Cui

Training LLMs with Human Feedback Just Got Easier (and More Reliable)

Xiang Ji|Sanjeev Kulkarni|Mengdi Wang|Tengyang Xie

How Generative AI Will Revolutionize Next-Gen Networks

Han Zhang|Akram Bin Sediq|Ali Afana|Melike Erol-Kantarci

Can AI Tell Fact From Fiction? New Research Tackles Uncertainty in Language Models

Lukas Aichberger|Kajetan Schweighofer|Mykyta Ielanskyi|Sepp Hochreiter

The first platform built for prompt engineering