Research Papers

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Unlocking Text Adventures: How AI Plans in Interactive Worlds

Li Zhang|Peter Jansen|Tianyi Zhang|Peter Clark|Chris Callison-Burch|Niket Tandon

Can Small AI Models Actually Keep Us Safe?

Ohjoon Kwon|Donghyeon Jeon|Nayoung Choi|Gyu-Hwung Cho|Changbong Kim|Hyunwoo Lee|Inho Kang|Sun Kim|Taiwoo Park

Unlocking Dialogue: How AI Uncovers Hidden Structures in Conversation

Jiahui Xu|Feng Jiang|Anningzhe Gao|Haizhou Li

Can AI Be Tricked into Misbehaving? Exploring LLM Vulnerabilities

Shuyuan Liu|Jiawei Chen|Shouwei Ruan|Hang Su|Zhaoxia Yin

Unlocking AI’s Reasoning Power: A New Distillation Trick

Chengwei Dai|Kun Li|Wei Zhou|Songlin Hu

Unlocking AI’s Long-Term Memory: The Quest for Longer Contexts

Chaochen Gao|Xing Wu|Qi Fu|Songlin Hu

DevEval: Evaluating LLMs on Real-World Code Repositories

Jia Li|Ge Li|Yunfei Zhao|Yongmin Li|Huanyu Liu|Hao Zhu|Lecheng Wang|Kaibo Liu|Zheng Fang|Lanshen Wang|Jiazheng Ding|Xuanming Zhang|Yuqi Zhu|Yihong Dong|Zhi Jin|Binhua Li|Fei Huang|Yongbin Li

Unlocking Time in Videos: How AI Pinpoints Actions

Young Chol Song

Can LLMs Learn Just From Examples? The In-Context Learning Mystery

Hao Zhao|Maksym Andriushchenko|Francesco Croce|Nicolas Flammarion

The first platform built for prompt engineering