03/23: Hiring a postdoc to join the Villum Young Investigator project on pixel-based language modelling. Applications due by 29 March.

02/23: One paper accepted at CVPR 2023 on lightweight training for image captioning with retrieval augmentation. Congratulations to Rita!

02/23: One paper accepted at SCIA 2023 on cleaner label spaces for object detectors. Congratulations to Davide!

02/23: Talk at Chalmers University of Technology.

01/23: Received a five year Villum Young Investigator grant from the Velux Foundation to build a group with 2 Ph.D Fellows and 1 Postdoc to focus on pixel-based langauge models.

01/23: Two papers accepted at EACL 2023 on retrieval-augmented image captioning and a dataset for multilingual financial text classification. Congratulations to Rita and Rasmus!

01/23: One paper accepted at ICLR 2023 on pixel-based language modelling. Congratulations to Phillip!

01/23: Talk at MIT.

12/22: Keynote at MMLow.

12/22: Talk at KUIS AI.

10/22: Talk at Peking University.

10/22: Two papers accepted at EMNLP 2022 on multilingual multimodal learning with machine translated text and on the effectiveness of Transformers for long document classification. Congratulations to Chen and Dai!

09/22: Talk at (Dis)embodiment.

09/22: Talk at Adobe Research.

08/22: Paper accepted at the International Conference on Frontiers in Handwriting Recognition.

08/22: Talk at University of Edinburgh.

08/22: Wenyan Li has joined the group as a Ph.D Fellow.

07/22: New preprint on pixel-based language modelling. We released the code and the pretrained model too.

06/22: Dynabench Data Collection Grant from Facebook.

05/22: Workshop on Multilingual Multimodal Learning at ACL 2022.

05/22: Emanuele has a paper accepted to ICML 2022 on a multilingual multimodal language understanding benchmark.