Jiuxiang Gu is a Research Scientist in the Document Intelligence Lab (DIL) of Adobe Research at Maryland site. He obtained his Ph.D. degree at Nanyang Technological University (NTU), Singapore, where he focused on the fusion of deep learning and reasoning for computer vision, such as image captioning, cross-modal retrieval, scene graph generation, visual question answering and so on.

His research interests lie at the intersection of computer vision and natural language processing. His contact email is jigu@adobe.com, and more information is available on his personal website.


Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU models

Du, M., Manjunatha, V., Jain, R., Deshpande, R., Dernoncourt, F., Gu, J., Sun, T., Hu, X. (Jun. 11, 2021)

NAACL 2021