🚨 A paper you all have been waiting for 🤩 "PokemonChat: Auditing #ChatGPT for #Pokemon Universe Knowledge", a CoAStAL NLP collab. with Laura Cabello, and Jiaang Li, available now at SSRN 📘 : papers.ssrn.com/sol3/papers.cf… A 🧵: 1/n

Rita Ramos will present her work on Retrieval-augmented Image Captioning at #EACL2023. You should check this out if you're interested in the role of context / augmentation in multimodality. Paper: aclanthology.org/2023.eacl-main… Session: Poster 4 on May 3 at 1115-1245

We're presenting SmallCap, a lightweight image captioning model with retrieval augmentation at #CVPR2025. If you're around, come chat with us! #CVPR2023 Yova Kementchedjhieva

I'm hiring a postdoc for 18 months to work with us on tokenization-free NLP in Copenhagen. Applications are due by August 31: di.ku.dk/english/about/…. Don't hesitate to reach out with informal inquiries.

The 2023 edition of REST-CL came to an end. Also this year, we go home with new friends and research ideas. It has been amazing!

For those who aim to use the *best* up-to-date encoder-only PLMs for #legalNLP on Hugging Face, consider: (English, up to 512/4096 tokens) huggingface.co/lexlms/legal-r… huggingface.co/lexlms/longfor… (Multilingual, up to 512/4096 tokens) huggingface.co/joelito/legal-… huggingface.co/joelito/legal-…

I am hiring up to two Ph.D students to work on tokenization-free language modelling at the University of Copenhagen. Find out more about our group: lampgroup.github.io and apply by November 15th and list me as a potential supervisor.

Check out our new preprint on improving automatic VQA evaluation with the power of Large Language Models (LLMs)! 🤖📊 arxiv.org/abs/2310.02567 w/ Benno Krojer and Aishwarya Agrawal 🧵👇

🚨 Check out our new preprint "On the Interplay between Fairness and Explainability" together with Emanuele Bugliarello & Ilias Chalkidis from CoAStAL NLP. 📝arxiv.org/pdf/2310.16607… In this paper, we systematically investigate how optimizing for fairness improves explainability & vice versa

Last chance to apply for a Ph.D position to work on tokenization-free language modelling. Applications are due in just one week through the ELLIS Portal ellis.eu/news/ellis-phd…

Congratulations to Emanuele Bugliarello for defending his Ph.D thesis yesterday! His examiners were Serge Belongie Mirella Lapata and Mohit Bansal. If you are interested in multimodal learning, you can read On Multimodal Representations Learned at Scale di.ku.dk/english/resear…

✴ Hiring a Postdoctoral Researcher ✴ I am hiring a postdoc with a background in *vision and language processing*, on a 2/3 year contract. Application deadline: 15 Feb 2024 Start: ASAP Apply here: mbzuai.ac.ae/vacancy/postdo… and contact me here or via email. #NLProc #hiring

📢 I am hiring two Ph.D students at the University of Copenhagen to work on topics related to multimodal and multilingual processing, trustworthiness in LLMs, and tokenization-free NLP. More about the group: lampgroup.github.io Apply by February 29 jobportal.ku.dk/phd/?show=1609…

Introducing “Towards Privacy-Aware Sign Language Translation at Scale” We leverage self-supervised pretraining on anonymized videos, achieving SOTA ASL-to-English translation performance while mitigating risks arising from biometric data. 📄: arxiv.org/abs/2402.09611 🧵(1/9)