Roman Plaud

Here is the recording with the slides for those interested!
🎤 youtu.be/UONvP1TL0-g?...
📊 drive.google.com/file/d/14ZIo...
📑 arxiv.org/pdf/2410.02724

@cohere.com @cohereforai.bsky.social

Having a drink after the first day of the skada code sprint. Thanks to all the participants tons of nice things are coming. scikit-adaptation.github.io

🚀Proud to share our work on the training dynamics in Transformers with Wassim Bouaziz & @viviencabannes.bsky.social @Inria @MetaAI

📝Easing Optimization Paths arxiv.org/pdf/2501.02362 (accepted @ICASSP 2025 🥳)

📝Clustering Heads 🔥https://arxiv.org/pdf/2410.24050

🖥️ github.com/facebookrese...

1/🧵

🚨So, you want to predict your model's performance at test time?🚨

💡Our NeurIPS 2024 paper proposes 𝐌𝐚𝐍𝐨, a training-free and SOTA approach!

📑 arxiv.org/pdf/2405.18979
🖥️https://github.com/Renchunzi-Xie/MaNo

1/🧵(A surprise at the end!)

🚀 Did you know you can use the in-context learning abilities of an LLM to estimate the transition probabilities of a Markov chains?

The results are pretty exciting ! 😄

The more colorful your sweat is the more people come to see your poster

Just got back from EMNLP, my first-ever conference!
Met amazing people, learned so much, and presented my paper on Hierarchical Text Classification: aclanthology.org/2024.conll-1....
Already excited for the next one!