X(Twitter) / Blog(!!!) / Zhihu / Google Scholar / Github / Huggingface / CV
<aside> <img src="https://prod-files-secure.s3.us-west-2.amazonaws.com/7af8f684-8d20-4c20-a9b6-e6c975b8cb4c/f44c448b-c9eb-445b-8a71-5c84d57223ec/WX20240909-1323252x.png" alt="https://prod-files-secure.s3.us-west-2.amazonaws.com/7af8f684-8d20-4c20-a9b6-e6c975b8cb4c/f44c448b-c9eb-445b-8a71-5c84d57223ec/WX20240909-1323252x.png" width="40px" />
Nijika: Qingyu is an undergraduate student from Zhejiang University, class of 2022. He is pursuing a dual degree in English and Computer Science.
Intern @Hedra, previous @Westlake University @ZJUNLP.
His research is centered on the intersection of Alignment and Science of LLM.
</aside>
StableMask: Refining Causal Masking in Decoder-only Transformer [ICML'24] ArXiv / Github / X(Twitter) Qingyu Yin, Xuzheng He, Xiang Zhuang, Yu Zhao, Jianhua Yao, Xiaoyu Shen, Qiang Zhang
Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning [EMNLP'24 Findings] ArXiv / Github / X(Twitter) Qingyu Yin, Xuzheng He, Chak Tou Leong, Fan Wang, Yanzhao Yan, Xiaoyu Shen, Qiang Zhang
Constraining Alignment Accurately with a Sparse AutoEncoder [Preprint] ArXiv / Github / X(Twitter) Qingyu Yin, Chak Tou Leong*, Hongbo Zhang, Minjun Zhu, Hanqi Yan, Qiang Zhang, Yulan He, Wenjie Li, Jun Wang, Yue Zhang, Linyi Yang
Understanding Feature Dynamics in Language Model Safety [Preprint] Qingyu Yin, Chak Tou Leong, Linyi Yang, Qiang Zhang
Induction Head Toxicity Mechanistically Explains Repetition Curse in Large Language Models [Preprint] Qingyu Yin, Shuxun Wang, Chak Tou Leong, Linyi Yang, Qiang Zhang
Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region [Preprint] ArXiv / Github / X(Twitter) / Project Page Chak Tou Leong, Qingyu Yin, Jian Wang, Wenjie Li
Magic 1-For-1: Generating One Minute Video Clips within One Minute [Preprint] ArXiv / Github / X(Twitter) / Project Page Hongwei Yi, Shitong Shao, Tian Ye, Jiantong Zhao, Qingyu Yin, Michael Lingelbach, Li Yuan, Yonghong Tian, Enze Xie, Daquan Zhou
MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice [Preprint] ArXiv / Github / X(Twitter) / Project Page Hongwei Yi, Tian Ye, Shitong Shao, Xuancheng Yang, Jiantong Zhao, Hanzhong Guo, Terrance Wang, Qingyu Yin, Zeke Xie, Lei Zhu, Wei Li, Michael Lingelbach, Daquan Zhou
Scientific large language models: A survey on biological & chemical domains [ACM Computing] ArXiv / Github / X(Twitter) / Project Page Qiang Zhang, Keyan Ding, Tianwen Lv, Xinda Wang, Qingyu Yin, Yiwen Zhang, Jing Yu, Yuhao Wang, Xiaotong Li, Zhuoyi Xiang, Xiang Zhuang, Zeyuan Wang, Ming Qin, Mengyao Zhang, Jinlu Zhang, Jiyu Cui, Renjun Xu, Hongyang Chen, Xiaohui Fan, Huabin Xing, Huajun Chenu
https://embed.notionlytics.com/wt/ZXlKM2IzSnJjM0JoWTJWVWNtRmphMlZ5U1dRaU9pSnpiSHB2U21scmNVUnpOVnBhUVVWcldrUnJXU0lzSW5CaFoyVkpaQ0k2SW1VNE9HVm1NRGszTjJOak5UUXpNVE5oWlRRM05UWXpOR1kyWVdObVltRTBJbjA9
