Are you looking to do a Ph.D/Postdoc in multimodal learning? I'm supporting applications to join my group with a fully-funded @DataScienceDK Fellowship. Ph.D: ddsa.dk/phdfellowshipp… Postdoc: ddsa.dk/postdocfellows… Apply: March 23 Start: September 23

CoAStaL [coastalcph.github.io] will hire several 1-3y postdocs next year. Topics: fair ASR, historical handwriting, explainability, NLP-meets-philosophy-and-cogsci. Email [email protected] if you're interested in any of the above.

Thrilled to receive a grant from Villum Fonden to carry out blue-skies research on tokenization-free NLP veluxfoundations.dk/en/about/proje… I will hire Ph.Ds and Postdocs to build up the group so feel free to reach out. We're starting off with a paper at #ICLR2023 openreview.net/forum?id=FkSp8…

📢 I am hiring a postdoc to join our project on pixel-based natural language processing. The position is based in Copenhagen 🇩🇰 for 18 months. Applications are due by March 29 employment.ku.dk/faculty/?show=…. Informal inquiries are welcome.

Introducing SeamlessM4T, the first all-in-one, multilingual multimodal translation model. This single model can perform tasks across speech-to-text, speech-to-speech, text-to-text translation & speech recognition for up to 100 languages depending on the task. Details ⬇️

anon policy survey is out: tinyurl.com/aclarxivpolicy

In Text Rendering Strategies for Pixel Language Models with Jonas Færch Lotz Phillip Rust and Elizabeth Salesky, we design new text renderers for visual language processing to improve performance or to squeeze the model down to just 22M parameters. See it in Poster Session 2 on Friday 8th.

In PHD: Pixel-Based Language Modeling of Historical Documents with Nadav Borenstein Phillip Rust and Isabelle Augenstein, we apply pixel language models to processing historical document and to more standard NLP classification tasks too. See it in Poster Session 6 on Sunday 10th.

New preprint "Improving Language Understanding from Screenshots" w/ Zirui "Colin" Wang Adithya Bhaskar Danqi Chen. We improve language understanding abilities of screenshot LMs, an emerging family of models that processes everything (including text) via visual inputs arxiv.org/abs/2402.14073

I will be presenting this work in-person at ACL🇹🇭 this week. Drop by if you'd like to chat! Oral: Today (Monday) 16:30 Poster: Tuesday (Tomorrow) 10:30 - 12:00