Our paper introducing Alternators has been accepted at TMLR. Alternators are a new class of generative models that outperform state-space models, such as Mambas, and diffusion models such as ScoreGrad. Check it out!
Paper: arxiv.org/abs/2405.11848
Code: github.com/vertaix/Alternators
#MLSky #Vertaix

📢A unique fully funded three-years PhD position is open at POLITO and EURECOM.
Title: Enhancing Educational Storytelling with Human-Centered AI in the LLM Era
Application deadline: April 28, 2025
Details: www.linkedin.com/feed/update/...

Amazing interview with Yang Song, one of the key researchers we have to thank for diffusion models.

The most important lesson: be fearless! The community's view on score matching was quite pessimistic at the time, he went against the grain and made it work at scale!

www.youtube.com/watch?v=ud6z...

I just shared a new article, "The State of Reasoning Models", where I am exploring 12 new research articles on improving the reasoning capabilities of LLMs (all published after the release of DeepSeek R1): magazine.sebastianraschka.com/p/state-of-l...

Happy reading!

Happy to share that our paper, "Information Theoretic Text-to-Image Alignment," has been accepted at ICLR 2025! 🚀

Kudos to the team: Chao Wang, the PhD student leading this work, Alessandro Finamore, Max Gallo, and Giulio Franzese.

arxiv.org/abs/2405.20759

Really excited about this! We note a connection between diffusion/flow models and neural/latent SDEs. We show how to use this for simulation-free learning of fully flexible SDEs. We refer to this as SDE Matching and show speed improvements of several orders of magnitude.

arxiv.org/abs/2502.02472

How do tokens evolve as they are processed by a deep Transformer?

With José A. Carrillo, @gabrielpeyre.bsky.social and @pierreablin.bsky.social, we tackle this in our new preprint: A Unified Perspective on the Dynamics of Deep Transformers arxiv.org/abs/2501.18322

ML and PDE lovers, check it out!

We’re organizing once again the Gznerative Modeling Summer school this spring on the Côte d’Azur, merged for the occasion with SFdS’s Statlearn!
Applications are open!

Excited about

🎓 Generative Modeling Summer School / Statlearn
🗓️ Mar 31 - Apr 4, 2025, France

ℹ️ gemss.ai
🎟️ Deadline: Jan 27, 2025

🧑‍🏫 Yingzhen Li, @stephanmandt.bsky.social, Aude Sportisse, Anna Korba, @glouppe.bsky.social, @jesfrellsen.bsky.social, @pamattei.bsky.social, @jmtomczak.bsky.social, TBA

The slides of my NeurIPS lecture "From Diffusion Models to Schrödinger Bridges - Generative Modeling meets Optimal Transport" can be found here
drive.google.com/file/d/1eLa3...

Meet EULER (EURECOM Language Model for Education and Research) and our new #Socratic LLM for AI-Driven Education, eurecom-blog.medium.com/eurecoms-soc...
Model available @huggingface.bsky.social and @ollama.bsky.social
#LLM #RAG #EduTech

Discrete diffusion has become a very hot topic again this year. Dozens of interesting ICLR submissions and some exciting attempts at scaling. Here's a bibliography on the topic from the Kuleshov group (my open office neighbors).

github.com/kuleshov-gro...

1/ I work in #NeuroAI, a growing field of research, which many people have only the haziest conception of...

As way of introduction to this research approach, I'll provide here a very short thread outlining the definition of the field I gave recently at our BRAIN NeuroAI workshop at the NIH.

🧠📈

🧠 Come work with us! In addition to our postdoc position on modelling, our lab at @institutpasteur.bsky.social we also seek a postdoc to help us create the most complete open atlas of brain folding development! This is part of our ERC Synergy project Unfold (unfold-lab.github.io). Join us! (1/10)

We are organising the First International Conference on Probabilistic Numerics (ProbNum 2025) at EURECOM in southern France in Sep 2025. Topics: AI, ML, Stat, Sim, and Numerics. Reposts very much appreciated!

probnum25.github.io