Research Papers

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Can AI Hack and Heal Itself? PenHeal Framework Tested

Junjie Huang|Quanyan Zhu

Unlocking the Power of Massive Multi-Agent Simulations with AgentScope

Xuchen Pan|Dawei Gao|Yuexiang Xie|Yushuo Chen|Zhewei Wei|Yaliang Li|Bolin Ding|Ji-Rong Wen|Jingren Zhou

Unlocking Multimodal AI: A New Breakthrough in Vision-Language Models

Vedanshu|MM Tripathi|Bhavnesh Jaint

The Myth of AI Memorization: Do Large Language Models Really Remember?

Jing Huang|Diyi Yang|Christopher Potts

Making LLMs Faster: The Early-Exit Strategy

Ruijie Miao|Yihan Yan|Xinshuo Yao|Tong Yang

Can AI Analyze Financial Statements Better Than Humans?

Alex Kim|Maximilian Muhn|Valeri Nikolaev

Taming the Memory Beast: How to Optimize LLM KV Cache

Luohe Shi|Hongyi Zhang|Yao Yao|Zuchao Li|Hai Zhao

Do AI Chatbots Have Political Biases?

Jan Batzner|Volker Stocker|Stefan Schmid|Gjergji Kasneci

Unlocking AI's Potential: Revolutionizing Healthcare Chatbots with QB-RAG

Eric Yang|Jonathan Amar|Jong Ha Lee|Bhawesh Kumar|Yugang Jia

The first platform built for prompt engineering