Read Nathan's thread and (bsky.app/profile/nthn...) to get more details and the paper to get an even better picture: arxiv.org/abs/2510.25771.
12.11.2025 23:18
👍 1
🔁 1
💬 0
📌 0
Read Nathan's thread and (bsky.app/profile/nthn...) to get more details and the paper to get an even better picture: arxiv.org/abs/2510.25771.
The experiments are really interesting, giving insights into the training of such models, the impact of pre-training data, and the huge problem of test set leakage in pretraining data, a problem that we show has an impact on some very popular LLMs!
Congratulations to @nthngdy.bsky.social, @wissamantoun.bsky.social and Rian Touchent (who worked under the supervision of @zehavoc.bsky.social, @bensagot.bsky.social, Éric de La Clergerie and me) on the training of these generative models for French, English and code.
@inriaparisnlp.bsky.social brought you CamemBERT, and we now bring you Gaperon (for non-cheese connoisseurs, it’s a cheese that’s flavoured with pepper and garlic 🧀 ).
📊 Preliminary ranking of WMT 2025 General Machine Translation benchmark is here!
But don't draw conclusions just yet - automatic metrics are biased for techniques like metric as a reward model or MBR. The official human ranking will be part of General MT findings at WMT.
arxiv.org/abs/2508.14909
Merci à l'équipe organisatrice des journées #istex pour l'invitation ! Très heureux d'avoir pu présenter les avancées de MaTOS à Nancy devant un public de connaisseurs. @cnrs-inist.bsky.social
Aina Garí Soler - "Word Meaning Representation and Negotiation" - ALMAnaCH seminar 21st March 2025 at 11am CET
We are excited for our next seminar, which will be given by Aina Garí Soler (Inria, @inriaparisnlp.bsky.social) on "Word Meaning Representation and Negotiation" on Friday 21st March at 11am CET. Connection link to be shared on the day. Details here: almanach.inria.fr/seminars-en....!
Lydia Nishimwe est finaliste du concours "Ma thèse en 180 secondes" à Sorbonne Université ! Venez la soutenir le lundi 10 mars à 18h 🎤 🎓👏
Guess what? The jubilee 🎉 20th iteration of WMT General MT 🎉 is here, and we want you to participate - as the entry barrier to make an impact is so low!
This isn’t just any repeat. We’ve kept what worked, removed what was outdated, and introduced many exciting new twists! Among the key changes are:
We are thrilled to announce our next seminar by Syrielle Montariol @smontariol.bsky.social (EPFL) entitled "Multimodal perception and reasoning" on Friday 21st February at 11am CET. Connection link to be shared on the day. Details here: t.co/pPbWfkALM4!
I am happy to announce that our paper "In-context Example Selection via Similarity Search Improves Low-resource Machine Translation" was accepted to the #NAACL2025 Findings 🤩🔥.
What is this about?
TAGS: Machine Translation (MT), High/Low -resource languages (H/LRLs).
🧵
1/10
Cécile Pierrot & Camille Desenclos - "Percer le secret des lettre chiffrées de Charles Quint : un travail interdisciplinaire" - ALMAnaCH seminar 7th February 2025 at 11am CET
We are excited for our next seminar by Cécile Pierrot (Inria) & Camille Desenclos (Université de Picardie & Inria) entitled "Percer le secret des lettres chiffrées de Charles Quint: un travail interdisciplinaire" on Friday 7th February at 11am CET. Details here: t.co/pPbWfkALM4!