@inproceedings{ijcai2024p0339, title = {ScreenAI: A Vision-Language Model for UI and Infographics Understanding}, author = {Baechler, Gilles and Sunkara, Srinivas and Wang, Maria and Zubach, Fedir and Mansoor, Hassan and Etter, Vincent and Carbune, Victor and Lin, Jason and Chen, Jindong and Sharma, Abhanshu}, booktitle = {Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, {IJCAI-24}}, publisher = {International Joint Conferences on Artificial Intelligence Organization}, editor = {Kate Larson}, pages = {3058--3068}, year = {2024}, month = {8}, note = {Main Track}, doi = {10.24963/ijcai.2024/339}, url = {https://doi.org/10.24963/ijcai.2024/339}, }