Learning without training Google researchers explore the implicit dynamics of in-context learning. "Implicit weight updates from ICL mirror the effect of actual fine-tuning on the same data." This one is more technical but much needed. The findings:

🚗 Ever wondered if an AI model could learn to drive just by watching YouTube? 🎥👀 We trained a 1.2B parameter model on 1,800+ hours of raw driving videos. No labels. No maps. Just pure observation. And it works! 🤯 🧵👇 [1/10]

📚🔍Excited to share our work at #NeurIPS2024! Dive into representation learning, optimization, explainability, VLMs & LLMs, and more. Check out our blog post to know more about our 7 papers: https://t.co/gaLDkkYsQe 🧵👇

Trying to move to 🦋. Same id as here😎.

Working on ill-posed machine learning tasks, interested in multi-heads neural networks and data #uncertainty quantification ? Sharing here our latest research, which will be presented at @NeurIPSConf in December.

"GEPS: Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning" by @ArmandKassai, @JorgeMifsut, @yuanyinnn, Jean Noël Vittaut, Patrick Gallinari accepted as conference paper at #NeurIPS2024 ! ➡️ https://t.co/ztSKO05ogo 🖥️ https://t.co/Pz4YSrEYLw

*cries in confirmed reviewer*

🔵🏛️ #IVG dans la Constitution : le Congrès a très largement approuvé le texte qui lui était soumis, faisant de la France le premier pays au monde à inscrire l'IVG dans sa Constitution. ➡️ Récit du Congrès et détail du scrutin, à lire : https://t.co/6JQE1dnR6G #DirectAN

Supervisor's reaction when trainee explains that their 2 week training run failed and the only evidence they have is the loss plot.

À chaque fois que je constate qu'un poste en ML exige une autorisation de travail dans une offre d'emploi publiée en France, je m'interroge sur sa signification. Si le salaire peut me permettre d'obtenir un passeport talent, pourquoi pourrais-je rencontrer des problèmes ?

https://t.co/QdgGsBpBR3

The ML ecosystem in France is on fire🔥 It has amazing talent and resources. Here are 10 facts you might not know: 1. There are great research labs - from @MistralAI and @kyutai_labs to large ones from @AIatMeta and @GoogleDeepMind. The Llama 2 and CodeLlama authors are based in

Thank you to the NeurIPS DIA chairs for conducting the survey on participation barriers, giving me the chance to share my experiences. Being a foreigner in a country where nearly nobody needs a visa to attend a conference isn’t easy. Hope that one day I can enjoy the conference.

I don’t now if it is related but I just discovered I made it onto the list of Top Reviewers for the very first time at NeurIPS 2023 alongside my lab colleagues! It feels great.

How long have you been there?

But no worries! We still have the one and the only NeurIPS@Paris at SCAI!

NeurIPS season is coming! Great news: Got a complimentary registration for NeurIPS 2023 as a reviewer! 🎉 Bad news: No available US visa appointment in France. 😇 I guess I just don’t have enough chance to attend an in-person conference.

The story of my life in mathematics.

Me reviewing my assigned ICLR papers: Am I reading a conference paper?

Tutorial on Physics-aware Deep Learning @ECMLPKDD, by @yuanyinnn and Patrick Gallinari Slides available here: