Research Papers

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Do Multimodal LLMs Really Perceive?

Kim Sung-Bin|Oh Hyun-Bin|JungMok Lee|Arda Senocak|Joon Son Chung|Tae-Hyun Oh

Can AI Truly Be Creative in Math?

Junyi Ye|Jingyi Gu|Xinyun Zhao|Wenpeng Yin|Guiling Wang

Boosting LLM Inference Speed with Speculative Decoding

Sudhanshu Agrawal|Wonseok Jeon|Mingu Lee

Making AI More Trustworthy: Fighting Hallucinations

Yiqing Xie|Wenxuan Zhou|Pradyot Prakash|Di Jin|Yuning Mao|Quintin Fettes|Arya Talebzadeh|Sinong Wang|Han Fang|Carolyn Rose|Daniel Fried|Hejia Zhang

AI Can Now Speak Database: Mastering Multiple Dialects

Zhisheng Lin|Yifu Liu|Zhiling Luo|Jinyang Gao|Yu Li

Boosting AI Tool Use with Better Dialogue

Zezhong Wang|Xingshan Zeng|Weiwen Liu|Liangyou Li|Yasheng Wang|Lifeng Shang|Xin Jiang|Qun Liu|Kam-Fai Wong

Can AI Generate Profitable Stock Signals?

Yining Wang|Jinman Zhao|Yuri Lawryshyn

Can LLMs Revolutionize Agile Software Development?

Ahmed R. Sadik|Sebastian Brulin|Markus Olhofer|Antonello Ceravola|Frank Joublin

Is Chinese AI Safe? New Benchmark Puts LLMs to the Test

Hengxiang Zhang|Hongfu Gao|Qiang Hu|Guanhua Chen|Lili Yang|Bingyi Jing|Hongxin Wei|Bing Wang|Haifeng Bai|Lei Yang

The first platform built for prompt engineering