Research Papers

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Unlocking Chatbots: Supercharging LLMs for Effortless Conversations

Vishal Vivek Saley|Rocktim Jyoti Das|Dinesh Raghu|Mausam

Exposed! Your Private Texts Leaked from AI Gradients

Ivo Petrov|Dimitar I. Dimitrov|Maximilian Baader|Mark Niklas Müller|Martin Vechev

Taming Rogue AIs: Adversarial Training for Safer LLMs

Sophie Xhonneux|Alessandro Sordoni|Stephan Günnemann|Gauthier Gidel|Leo Schwinn

Beyond Human Feedback: A New Path to Align AI

Hao Sun|Mihaela van der Schaar

Can AI Solve Multilingual Puzzles? A New Benchmark Challenges the Limits

Hongyu Wang|Jiayu Xu|Senwei Xie|Ruiping Wang|Jialin Li|Zhaojie Xie|Bin Zhang|Chuyan Xiong|Xilin Chen

Secret Messages Hidden in Plain Sight: How LLMs Can Be Used for Covert Communication

Simen Gaure|Stefanos Koffas|Stjepan Picek|Sondre Rønjom

Making AI Forget: The Art of Machine Unlearning

Wenhan Chang|Tianqing Zhu|Heng Xu|Wenjian Liu|Wanlei Zhou

Unlocking Zero-Shot Image Power: How Multimodal LLMs Enhance Vision

Abdelrahman Abdelhamed|Mahmoud Afifi|Alec Go

Slashing AI Coding Costs: How Model Cascading Makes LLMs Cheaper

Boyuan Chen|Mingzhi Zhu|Brendan Dolan-Gavitt|Muhammad Shafique|Siddharth Garg

The first platform built for prompt engineering