Human Understanding
Human understanding, a multifaceted field encompassing cognitive processes and AI model capabilities, seeks to unravel how humans and machines comprehend information. Current research focuses on improving AI's ability to understand nuanced language, visual information, and complex relationships within data, employing techniques like multimodal large language models, hypergraph attention networks, and retrieval-augmented generation. These advancements have implications for various applications, including improved medical diagnosis, enhanced human-computer interaction, and more effective scientific knowledge extraction, but challenges remain in achieving truly robust and generalizable understanding in AI.
Papers
End-to-end Document Recognition and Understanding with Dessurt
Brian Davis, Bryan Morse, Bryan Price, Chris Tensmeyer, Curtis Wigington, Vlad Morariu
Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo
Chaoning Zhang, Kang Zhang, Trung X. Pham, Axi Niu, Zhinan Qiao, Chang D. Yoo, In So Kweon
Are Shortest Rationales the Best Explanations for Human Understanding?
Hua Shen, Tongshuang Wu, Wenbo Guo, Ting-Hao 'Kenneth' Huang
Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation
Wenxuan Wang, Wenxiang Jiao, Yongchang Hao, Xing Wang, Shuming Shi, Zhaopeng Tu, Michael Lyu