Associate Professor
University of Copenhagen
Department of Computer Science
Vibenshuset, 4th Floor, Lyngbyvej 2
København 2100
de@di.ku.dk (FAQ)
07/25: Talking about Pixel Language Models at the Tokenization Workshop at ICML.
06/25: Best Paper Honorable Award at the CVPR Visual Concepts Workshop!
06/25: Talking about Multilingual Vision-Language Research at the VLMs-4-All Workshop at CVPR.
05/25: Four papers at ACL 2025. Congratulations Anna, Nadav, Dan, and Constanza!
04/25: Recruiting a postdoc to join the Responsible AI for the People Project. Applications due by 1 May.
03/25: I will be an Associate Editor for JAIR from 2025--2028.
02/25: I am a Senior Area Chair for ACL 2025.
02/25: One paper in AI. Congratulations Alice!
01/25: Organized Workshop of Evaluation of Multi-Modal Generation
10/24: One paper at the NeurIPS 2024 FITML Workshop. Congratulations Ingo!
09/24: One paper at EMNLP 2024. Congratulations Wenyan!
06/24: I have been promoted to Associate Professor. Thanks to everyone that helped me in this achievement.
05/24: One paper at ACL 2024. Congratulations Wenyan!
04/24: One paper at MIDL 2024. Congratulations Vincent!
03/24: Two papers at NAACL 2024. Congratulations Semih and Rita!
01/24: One paper at EACL 2024. Congratulations Wenyan!
10/23: Three papers at EMNLP 2023. Congratulations to Laura, Jonas, and Nadav!
10/23: One paper at WMT. Congratulations Tosho!
10/23: Talking about Pixel Language Models at ML in PL 2023.
09/23: Recruiting up to two Ph.D students to work on tokenization-free language modelling. Apply through the ELLIS Ph.D Portal by November 15 and name me as a potential advisor.
07/23: Hiring a postdoc to join the Villum Young Investigator project on pixel-based language modelling. Applications due by 31 August.
07/23: Talking about Multimodal Learning at LXMLS 2023.
05/23: One paper at ACL 2023 on retrieval-augmented multilingual image captioning. Congratulations to Rita!
05/23: Talk at Young Statisticians Denmark
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 at CVPR 2023 on lightweight training for image captioning with retrieval augmentation. Congratulations to Rita!
02/23: One paper 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 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 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 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 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 to ICML 2022 on a multilingual multimodal language understanding benchmark.
03/22: Talk at University of Trento.
03/22: Talk at HiTZ Seminar Series.
11/21: Dana published a paper in Diagnostics on the role of AI assistance in detecting pathologies in CT and X-ray scans.
11/21: We received the Best Long Paper Award at EMNLP 2021!
11/21: Visually Grounded Reasoning across Languages and Cultures was to the published work track at the NeurIPS 2021 Workshop on Imagenet: Past, Present, and Future.
11/21: Talk at FBK on Visually Grounded Reasoning.
09/21: The data and baselines are available for the MaRVL challenge.
09/21: Three papers at EMNLP 2021 on understanding vision and language transformers, a linguistically diverse multilingual multimodal task, and multilingual domain adapation.
08/21: Iuliia has a paper at RepL4NLP with a dataset and models for multi-step relational reasoning in abstract images.
05/21: Emanuele has a paper to TACL on a mathematical and software framework that unifies Vision & Language BERTs. The paper explores the downstream differences between five models when trained on the same data with the same pretraining objectives.
02/21: Keynote at the Second Workshop on NLP Beyond Text.
01/21: Emanuele has a paper at EACL on improving compositional generalization in image captioning by integrating syntactic tags into image captioning models.
01/21: Area Chair for Language Grounding to Vision, Robotics and Beyond at ACL 2021
09/20: I'm hiring a postdoc to work on multimodal machine learning with medical records data. The application deadline is 15/10/2020 and I'm happy to answer informal questions.
09/20: Two papers at EMNLP 2020.
04/20: Three papers at ACL 2020.
03/20: Area Chair for Language Grounding to Vision, Robotics and Beyond at EMNLP 2020
03/20: Paper in Machine Translation
03/20: Paper in IEEE Selected Topics in Signal Processing
