Research Papers

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Safeguarding AI Vision: How SafeVLM Prevents Harmful Content

Zhendong Liu|Yuanbi Nie|Yingshui Tan|Xiangyu Yue|Qiushi Cui|Chongjun Wang|Xiaoyong Zhu|Bo Zheng

Unlocking the Future of Data: How AI is Revolutionizing Public Information

Anastasija Nikiforova|Martin Lnenicka|Petar Milić|Mariusz Luterek|Manuel Pedro Rodríguez Bolívar

Weight Decay With AdamW: How to Scale for Larger Models and Datasets

Xi Wang|Laurence Aitchison

Shrinking AI’s Data Footprint: Federated Fine-Tuning for LLMs

Huiwen Wu|Xiaohan Li|Deyi Zhang|Xiaogang Xu|Jiafei Wu|Puning Zhao|Zhe Liu

Unlocking Multilingual Magic in LLMs: How a Few Languages Can Teach Many

Shimao Zhang|Changjiang Gao|Wenhao Zhu|Jiajun Chen|Xin Huang|Xue Han|Junlan Feng|Chao Deng|Shujian Huang

How Sure Is Your AI? Measuring Confidence in Large Language Models

Xin Qiu|Risto Miikkulainen

Unlocking the Secrets of Time Series Forecasting with Large Time-Series Models

Thomas D. P. Edwards|James Alvey|Justin Alsing|Nam H. Nguyen|Benjamin D. Wandelt

Unlocking Visual Puzzles: How AI Masters Reasoning with Images

Qiji Zhou|Ruochen Zhou|Zike Hu|Panzhong Lu|Siyang Gao|Yue Zhang

Can LLMs Reason Faithfully? FiDeLiS Shows the Way

Yuan Sui|Yufei He|Nian Liu|Xiaoxin He|Kun Wang|Bryan Hooi

The first platform built for prompt engineering