Research Papers

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Can AI Match Data Schemas? An LLM Experiment

Marcel Parciak|Brecht Vandevoort|Frank Neven|Liesbet M. Peeters|Stijn Vansummeren

Can AI Chatbots Keep Their Facts Straight?

Tiziano Labruna|Bernardo Magnini

Securing AI’s Future: Confidential Computing on NPUs for Generative AI

Aritra Dhar|Clément Thorens|Lara Magdalena Lazier|Lukas Cavigelli

Can AI Tell Who Wrote That? Unmasking Authors with InstructAV

Yujia Hu|Zhiqiang Hu|Chun-Wei Seah|Roy Ka-Wei Lee

How AI Can Help Write Better Meeting Minutes

Frederic Kirstein|Terry Ruas|Bela Gipp

Can LLMs Really Handle One Million Words?

Mo Li|Songyang Zhang|Yunxin Liu|Kai Chen

Can AI Remember How to Be Bad? The Past Tense Jailbreak

Maksym Andriushchenko|Nicolas Flammarion

Protecting Privacy in AI Text Generation: A New Approach

Kareem Amin|Alex Bie|Weiwei Kong|Alexey Kurakin|Natalia Ponomareva|Umar Syed|Andreas Terzis|Sergei Vassilvitskii

Training Massive LLMs on Just a Few GPUs

Pinxue Zhao|Hailin Zhang|Fangcheng Fu|Xiaonan Nie|Qibin Liu|Fang Yang|Yuanbo Peng|Dian Jiao|Shuaipeng Li|Jinbao Xue|Yangyu Tao|Bin Cui

The first platform built for prompt engineering