iiinova — where your digital self keeps evolving

Reposted by Ambroise Odonnat

Rémi Flamary @rflamary.bsky.social · 29/07/2025

SKADA-Bench : Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalities, has been published published in TMLR today 🚀. It was a huge team effort to design (and publish) an open source fully reproducible DA benchmark 🧵1/n. openreview.net/forum?id=k9F...

openreview.net

SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods...

Unsupervised Domain Adaptation (DA) consists of adapting a model trained on a labeled source domain to perform well on an unlabeled target domain with some data distribution shift. While many...

1167

Ambroise Odonnat @ambroiseodt.bsky.social · 22/07/2025

🚀 We are happy to organize the BERT²S workshop @neuripsconf.bsky.social 2025 on Recent Advances in Time Series Foundation Models. 🌐 berts-workshop.github.io 📜Submit by August 22 🎓Speakers and panelists: Chenghao Liu, Mingsheng Long, Zoe Piran, Danielle C. Maddix, Ameet Talwalkar, Qingsong Wen

052

Ambroise Odonnat @ambroiseodt.bsky.social · 24/06/2025

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

youtu.be

Ambroise Odonnat - Large Language Models as Markov Chains

YouTube video by Cohere

022

Ambroise Odonnat @ambroiseodt.bsky.social · 13/06/2025

🚀 Very happy to be presenting Large Language Models as Markov Chains at Cohere Labs on June 19th at 6 pm CET (Paris time)!! Huge thanks to Andrej Jovanović @cohere.com @cohereforai.bsky.social for the invitation 🤗 Paper: arxiv.org/pdf/2410.02724 Learn more: cohere.com/events/Coher...

030

Reposted by Ambroise Odonnat

Théo Gnassounou @tgnassou.bsky.social · 20/05/2025

Skada Sprint Alert: Contribute to Domain Adaptation in Python 📖 Machine learning models often fail when the data distribution changes between training and testing. That’s where Domain Adaptation comes in — helping models stay reliable across domains.

1126

Ambroise Odonnat @ambroiseodt.bsky.social · 28/02/2025

🤗Thanks a lot @haeggee.bsky.social and @mjaggi.bsky.social for having me in the MLO group at EPFL @icepfl.bsky.social to present "Large Language Models as Markov Chains". Slides are available on my website (link in thread). 🎉 New experiments with Llama and Gemma models in the updated paper!

142

Ambroise Odonnat @ambroiseodt.bsky.social · 12/02/2025

🤗 Very happy to have (humbly) contributed to this work! This is a collab with the usual open-source suspects from Inria, @polytechniqueparis.bsky.social and @univparissaclay.bsky.social. Check it out if you are interested in open-source reproducible research 😇

020

Reposted by Ambroise Odonnat

Oussama Zekri @ozekri.bsky.social · 04/02/2025

🚀 Policy gradient methods like DeepSeek’s GRPO are great for finetuning LLMs via RLHF. But what happens when we swap autoregressive generation for discrete diffusion, a rising architecture promising faster & more controllable LLMs? Introducing SEPO ! 📑 arxiv.org/pdf/2502.01384 🧵👇

162

Ambroise Odonnat @ambroiseodt.bsky.social · 04/02/2025

🚀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/🧵

164

Ambroise Odonnat @ambroiseodt.bsky.social · 25/01/2025

Happy to see Disentangled In-Context Learning accepted at ICLR 2025 🥳 Make zero-shot reinforcement learning with LLMs go brrr 🚀 🖥️ github.com/abenechehab/... 📜 arxiv.org/pdf/2410.11711 Congrats Abdelhakim (abenechehab.github.io) for leading it, always fun working with nice and strong people 🤗

github.com

GitHub - abenechehab/dicl: Official implementation of DICL (Disentangled In-Context Learning), featured in the paper Zero-shot Model-based Reinforcement Learning using Large Language Models.

Official implementation of DICL (Disentangled In-Context Learning), featured in the paper Zero-shot Model-based Reinforcement Learning using Large Language Models. - abenechehab/dicl

052

Ambroise Odonnat @ambroiseodt.bsky.social · 10/12/2024

🎤Presenting our work on Unsupervised Accuracy Estimation at #NeurIPS2024 this week! ✋🏾Poster Session 4 West - on Thu. at 4:30 pm 📍 Poster #4310 - East Exhibit Hall A-C DM me if you'd like to chat :)

020

Ambroise Odonnat @ambroiseodt.bsky.social · 06/12/2024

Checkout the new version of this awesome domain adaptation library! So nice to work with such good people 🤗

021

Ambroise Odonnat @ambroiseodt.bsky.social · 03/12/2024

🚨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!)

2166

Reposted by Ambroise Odonnat

Mathurin Massias @mathurinmassias.bsky.social · 27/11/2024

Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition! We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423

1235299

Ambroise Odonnat @ambroiseodt.bsky.social · 26/11/2024

Check this out, a low-hanging fruit of our recent work « Large Language Models as Markov Chains » arxiv.org/pdf/2410.02724

arxiv.org

0174