Desmond Elliott @delliott.bsky.social · 02/03/2026In the blog, I discuss papers and personal correspondence with researchers on their findings about inferring training data, model training procedures, stealing deployed models and system prompts. 111 0
Desmond Elliott @delliott.bsky.social · 04/02/2026📢 I am hiring a highly-motivated Ph.D student at the University of Copenhagen to work on tokenization-free NLP. Read our previous work in this topic: aclanthology.org/2025.emnlp-m... aclanthology.org/2023.emnlp-m... openreview.net/forum?id=FkS... Apply by March 8: employment.ku.dk/phd/?show=1563 0209 0
Desmond Elliott @delliott.bsky.social · 23/06/2025The participants brought a lot of energy, enthusiasm, and great posters to highlight their research: @antoniakrm.bsky.social and @saravera.bsky.social pictured. Finally, I want to think the Danish Data Science Academy, Carlsberg Foundation, and the Villum Foundation for supporting the event! 040 0
Desmond Elliott @delliott.bsky.social · 23/06/2025Huge thanks to everyone that attended the Copenhagen NLP Symposium last week. Thanks for our wonderful speakers @kylelo.bsky.social, @najoung.bsky.social, Yohei Oseki, @mziizm.bsky.social, and @loubnabnl.hf.co! @mariaa.bsky.social did a great job of summarizing the talks in these liveposts (quoted). 180 0
Desmond Elliott @delliott.bsky.social · 11/06/2025I am looking forward to meeting people working on multimodality at #CVPR2025. You can find me hopping between the @vlms4all.bsky.social and Visual Concepts Workshops on Thursday. Feel free to reach out if you want to grab a coffee ☕ or a beer 🍻 during the week! 010 0
Desmond Elliott @delliott.bsky.social · 28/02/2025I was reading a preprint from this week and I noticed, upon closer inspection, that 41/49 of the citations are from 2023--. It seems like the observation we made in 2020 (aclanthology.org/2020.acl-mai...) is becoming even more extreme in 2025. 060 0
Desmond Elliott @delliott.bsky.social · 12/09/2023Interesting talk by Tal Linzen at LSD this morning that included a surprising result about how much syntax can be learned from smaller corpora, such as CHILDES or Simple Wikipedia aclanthology.org/2023.acl-lon... 040 0
