Research Papers

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Unlocking Free Bits: Exploiting Symmetries in LLMs

Jiajun He|Gergely Flamich|José Miguel Hernández-Lobato

The Flip Attack: How Easy Is It to Jailbreak an LLM?

Yue Liu|Xiaoxin He|Miao Xiong|Jinlan Fu|Shumin Deng|Bryan Hooi

Unlocking Multilingual Math Skills in LLMs: A New Approach

Lucas Bandarkar|Benjamin Muller|Pritish Yuvraj|Rui Hou|Nayan Singhal|Hongjiang Lv|Bing Liu

Is ChatGPT Biased? Unmasking Hidden Biases in AI

Federico Torrielli

Can Robots Learn New Tricks? A New Benchmark Tests AI’s Ability to Generalize

Ricardo Garcia|Shizhe Chen|Cordelia Schmid

Can LLMs Really Auto-Complete Code Like a Pro?

Zhenyu Pan|Rongyu Cao|Yongchang Cao|Yingwei Ma|Binhua Li|Fei Huang|Han Liu|Yongbin Li

Unlocking AI’s Full Potential: FlashMask Boosts Transformer Speed

Guoxia Wang|Jinle Zeng|Xiyuan Xiao|Siming Wu|Jiabin Yang|Lujing Zheng|Zeyu Chen|Jiang Bian|Dianhai Yu|Haifeng Wang

Asking the Right Questions: How AI Can Steer Conversations

Shasha Guo|Lizi Liao|Jing Zhang|Cuiping Li|Hong Chen

Can AI Truly Learn? LLMs vs. Traditional Learning

Yeonsun Yang|Ahyeon Shin|Mincheol Kang|Jiheon Kang|Jean Young Song

The first platform built for prompt engineering