Sign in

François Rozet

@francois-rozet.bsky.social
810 followers 61 following 49 posts

datamancer, generative models, bayesian inference, dynamical systems, open-source software, phd with @glouppe.bsky.social

PostsRepliesMedia
Reposted by François Rozet
Lê Nguyên Hoang @science4all.org · 24/09/2026
Cette vidéo vient de sauter dans mon top @tournesol.app !! Elle montre comment un mélange d'IA de recommandation toxiques, d'IA génératives à portée de tous et de précarité économique dans des pays défavorisés, est en train d'anéantir les démocraties occidentales. tournesol.app/entities/yt:...
tournesol.app
How to rage bait Americans
Christophe
23111
Reposted by François Rozet
Gilles Louppe @glouppe.bsky.social · 08/09/2026
No matter what, it is so sad to witness how open scientific problems have become publicity stunts and trophies for some AI players. Notice how so little is mentioned about the science, the proof, and its implications.
0213
Reposted by François Rozet
European Commission @ec.europa.eu · 02/08/2026
As of today, the use of AI becomes more transparent in the EU. Here’s how EU law makes sure AI works for you, in full openness ↓
Visual featuring a hand holding up a plain green card, similar to a referee's card. On the left are black labels with white text reading "AI", "AI MODIFIED", and "AI GENERATED". Below, bold text reads "The label says it all." The European Union logo appears in the top-right corner.
29607214
François Rozet @francois-rozet.bsky.social · 10/07/2026
Normalizing flows have fallen out of fashion as research topics, but they are still going strong in probabilistic ML for Science applications. Zuko has just crossed the 500k downloads, becoming the most downloaded NF library! pepy.tech/projects/zuko
pepy.tech
zuko · 501.5k downloads on PyPI
zuko has been downloaded 501.5k times. Normalizing flows in PyTorch See daily PyPI downloads, version splits, and 5-year history on pepy.tech.
141
Reposted by François Rozet
Gilles Louppe @glouppe.bsky.social · 24/05/2026
I'm watching my students slowly lose the ability to think, one AI prompt at a time. Not through cheating. Through doing everything right. So I tried something maybe unusual: I wrote a novella about it. Or rather, Claude wrote it, and that's my point. Give it a chance at glouppe.github.io/atrophy
4114
Reposted by François Rozet
Gilles Louppe @glouppe.bsky.social · 22/05/2026
"Accept (spotlight)" at ICML'26 😎 Our paper brings particle filters back to life: autoregressive diffusion models + posterior sampling yield optimal proposals for Bayesian filtering, scaling up to GenCast-sized systems. arxiv.org/abs/2605.20028 w/ Thomas Savary and @francois-rozet.bsky.social
arxiv.org
Training-Free Bayesian Filtering with Generative Emulators
Bayesian filtering is a well-known problem that aims to estimate plausible states of a dynamical system from observations. Among existing approaches to solve this problem, particle filters are theoret...
03911
Reposted by François Rozet
Gilles Louppe @glouppe.bsky.social · 12/02/2026
So how does it work? Meet Miniature (mini + IA, get it?), a complete AI agent in ~225 lines of Python. No frameworks, no abstractions. Code: github.com/glouppe/miniature
github.com
GitHub - glouppe/miniature
Contribute to glouppe/miniature development by creating an account on GitHub.
4297
François Rozet @francois-rozet.bsky.social · 02/12/2025
I'll be in Copenhagen from Tuesday to Saturday for the @euripsconf.bsky.social experiment! Please let me know if you want to chat about diffusion, flow, ml for science, or anything really. 🇩🇰
030
Reposted by François Rozet
Gilles Louppe @glouppe.bsky.social · 27/11/2025
Our Montefiore Science with AI lab will be at #NeurIPS2025 presenting 1 paper at the main conference and 3 papers at workshops. If you are attending, feel free to reach out with the crew to discuss science, AI, or just to say hi! (I won't attend this year unfortunately 🌱)
1156
Reposted by François Rozet
Typst @typst.app · 24/10/2025
You can now use PDFs as images: Just pass a PDF file to the image function and Typst will handle the rest. PDF images let you use vector and raster graphics from almost any other app. PDF images can be used for every Typst export target, including HTML.
Typst Code:
#image("logo.pdf")Logo of GlorboCorp
1121
Reposted by François Rozet
Typst @typst.app · 24/10/2025
Typst 0.14 is out now! Get ready for production with accessibility, PDFs as images, character-level justification, and more. Learn about more of the highlights in Typst 0.14 in the thread below ⤵️
Image saying Typst 0.14. It has a holographic effect. The background is a pattern of checkmarks, at the top, it changes to a pattern of the string "0.14". The horizontal bar across the top reads "Title Elementm Skewed Fractions, Table Subheaders, Accessible Documents, Character-level Justification, PDF/A compliance, PDF Images, Typed HTML API"
27718
Reposted by François Rozet
Gérôme Andry @Neurips2025 @gandry.bsky.social · 08/10/2025
🚀 After more than a year of work — and many great discussions with curious minds & domain experts — we’re excited to announce the public release of 𝐀𝐩𝐩𝐚, our latent diffusion model for global data assimilation! Check the repo and the complete wiki! github.com/montefiore-s...
github.com
GitHub - montefiore-sail/appa: Code for the publication "Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation".
Code for the publication "Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation". - montefiore-sail/appa
1207
Reposted by François Rozet
Signal @signal.org · 03/10/2025
We are alarmed by reports that Germany is on the verge of a catastrophic about-face, reversing its longstanding and principled opposition to the EU’s Chat Control proposal which, if passed, could spell the end of the right to privacy in Europe. signal.org/blog/pdfs/ge...
signal.org
4039242365
Reposted by François Rozet
Richard Gao @rdgao.bsky.social · 23/09/2025
I've been waiting some years to make this joke and now it’s real: I conned somebody into giving me a faculty job! I’m starting as a W1 Tenure-Track Professor at Goethe University Frankfurt in a week (lol), in the Faculty of CS and Math and I'm recruiting PhD students 🤗
media.tenor.com
a man wearing a white shirt and tie smiles in front of a window
ALT: a man wearing a white shirt and tie smiles in front of a window
3018831
Reposted by François Rozet
Lukas Heinrich @lukasheinrich.com · 04/09/2025
Big grant news today! I feel very lucky and honored for this opportunity from @erc.europa.eu . We will attempt to go for a big qualitative step up in how we use AI/ML to predict how particles interact with matter. Stoked to get started on this in 2026. we will release job advertisements soon!
9275
Reposted by François Rozet
Mike McCabe @michael-mccabe.bsky.social · 03/09/2025
Great work by @francois-rozet.bsky.social. Some really unexpected insights about compression in LDMs. It was such a privilege to have him with us @polymathicai.bsky.social!
011
François Rozet @francois-rozet.bsky.social · 03/09/2025
Does a smaller latent space lead to worse generation in latent diffusion models? Not necessarily! We show that LDMs are extremely robust to a wide range of compression rates (10-1000x) in the context of physics emulation. We got lost in latent space. Join us 👇
1278
François Rozet @francois-rozet.bsky.social · 26/07/2025
@neuripsconf.bsky.social removed the global rebuttal option?!? This was super useful (for authors AND reviewers AND area chairs AND readers) to get a summary of the common concerns of the reviewers and how the authors addressed them...
020
Reposted by François Rozet
Gaspard Lambrechts @gsprd.be · 16/07/2025
At #ICML2025, we will present a theoretical justification for the benefits of « asymmetric actor-critic » algorithms (#W1008 Wednesday at 11am). 📝 Paper: hdl.handle.net/2268/326874 💻 Blog: damien-ernst.be/2025/06/10/a...
ICML poster of the paper « A Theoretical Justification for Asymmetric Actor-Critic Algorithms » by Gaspard Lambrechts, Damien Ernst and Aditya Mahajan.
083
Reposted by François Rozet
Kyle Cranmer @kylecranmer.bsky.social · 10/07/2025
🎉 Great news: Our Machine Learning and Physical Sciences workshop will be back again this year! 🎉 Keep an eye out for updates on deadlines etc, we will be updating the website soon ml4physicalsciences.github.io #ML4PS2025
0329
Reposted by François Rozet
Kyle Cranmer @kylecranmer.bsky.social · 03/07/2025
As always, a very nice talk from Francois Lanusse: Generative Al for Inverse Problems and Forecasting Slides: eiffl.github.io/talks/Paris2...
0236
Reposted by François Rozet
ELLIS @ellis.eu · 12/06/2025
🏹 Job alert: PhD/postdoc positions in Scientific Foundation Models at the University of Liège (Belgium) 📍 Liège 🇧🇪 🔗 More info: bit.ly/43SJtUG
bit.ly
PhD/postdoc positions in Scientific Foundation Models at the University of Liège (Belgium)
The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of AI...
0135
Reposted by François Rozet
Gaspard Lambrechts @gsprd.be · 09/06/2025
📝 Our paper "A Theoretical Justification for Asymmetric Actor-Critic Algorithms" was accepted at #ICML! Never heard of "asymmetric actor-critic" algorithms? Yet, many successful #RL applications use them (see image). But these algorithms are not fully understood. Below, we provide some insights.
Slide showing three recent successes of reinforcement learning that have used an asymmetric actor-critic algorithm:
 - Magnetic Control of Tokamak Plasma through Deep RL (Degrave et al., 2022).
 - Champion-Level Drone Racing using Deep RL (Kaufmann et al., 2023).
 - A Super-Human Vision-Based RL Agent in Gran Turismo (Vasco et al., 2024).
1177
Reposted by François Rozet
Gilles Louppe @glouppe.bsky.social · 04/06/2025
Positions remain open! Both PhD and postdoctoral opportunities are available on scientific foundation models. An additional position is also available on AI for regional climate models (jointly with @xavierfettweis.bsky.social). Do not hesitate to apply!
0158
Reposted by François Rozet
Antoine Wehenkel @awehwe.bsky.social · 02/06/2025
📣 New paper alert — To be presented at ICML 2025! arxiv.org/abs/2405.08719 What does it really mean for a simulator to be misspecified, if our goal is to estimate parameters with calibrated uncertainty? A 🧵on our new method, RoPE, and what it means for real-world SBI ⬇️
arxiv.org
Addressing Misspecification in Simulation-based Inference through Data-driven Calibration
Driven by steady progress in deep generative modeling, simulation-based inference (SBI) has emerged as the workhorse for inferring the parameters of stochastic simulators. However, recent work has dem...
1184
Reposted by François Rozet
Gilles Louppe @glouppe.bsky.social · 23/05/2025
I can't recommend @francois-rozet.bsky.social enough👇He is both this excellent researcher and coder that any ML team would dream having onboard CC: @danilojrezende.bsky.social @awehwe.bsky.social @bkmi.bsky.social @yann-lecun.bsky.social @johannbrehmer.bsky.social
093
François Rozet @francois-rozet.bsky.social · 23/05/2025
📢 I am looking for AI post-doc/research/engineer positions in Europe (Paris, London, Zurich, ...) starting 2026. My work revolves around generative modeling and AI for Science, with 4+ publications at top conferences during my PhD. If you are hiring, please reach out! If not, please repost 🔁
21911
Reposted by François Rozet
Ben Miller @bkmi.bsky.social · 14/05/2025
We've open sourced Adjoint Sampling! It's part of a bundled release showcasing FAIR's research and open source commitment to AI for science. github.com/facebookrese... There's also a blog about the release ai.meta.com/blog/meta-fa...
github.com
GitHub - facebookresearch/adjoint_sampling: code for "Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching"
code for "Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching" - facebookresearch/adjoint_sampling
0223
Reposted by François Rozet
Charlie Marsh @crmarsh.com · 13/05/2025
Today, we’re announcing the preview release of ty, an extremely fast type checker and language server for Python, written in Rust. In early testing, it's 10x, 50x, even 100x faster than existing type checkers. (We've seen >600x speed-ups over Mypy in some real-world projects.)
1433284
Reposted by François Rozet
Gilles Louppe @glouppe.bsky.social · 29/04/2025
<proud advisor> Hot off the arXiv! 🦬 "Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation" 🌍 Appa is our novel 1.5B-parameter probabilistic weather model that unifies reanalysis, filtering, and forecasting in a single framework. A thread 🧵
25215
Reposted by François Rozet
matthieuterris.bsky.social @matthieuterris.bsky.social · 16/04/2025
For my first🧵on bsky, what if a single UNet could solve all inverse problems? In our latest preprint with Samuel Hurault, Maxime Song and @tachellajulian.bsky.social, we build a single multitask UNet for computational imaging — and show it generalizes surprisingly well 👇 arxiv.org/abs/2503.08915
1113
Reposted by François Rozet
Adrián Javaloy @javaloyml.bsky.social · 13/02/2025
Have you ever been curious to try Causal Normalizing Flows for your project but found them intimidating? Say no more 😜 I just released a small library to easily implement and use causal-flows: github.com/adrianjav/ca...
github.com
GitHub - adrianjav/causal-flows: CausalFlows: A library for Causal Normalizing Flows in Pytorch
CausalFlows: A library for Causal Normalizing Flows in Pytorch - adrianjav/causal-flows
14010
Reposted by François Rozet
Serge Belongie @serge.belongie.com · 30/03/2025
Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)
docs.google.com
NeurIPS participation in Europe
We seek to understand if there is interest in being able to attend NeurIPS in Europe, i.e. without travelling to San Diego, US. In the following, assume that it is possible to present accepted papers ...
6279161
François Rozet @francois-rozet.bsky.social · 18/03/2025
Just got a puzzle rated 3748 on @chess.com. Obviously, I failed 😂 The first move was insane, but the rest wasn't too far fetched.
010
Reposted by François Rozet
Gilles Louppe @glouppe.bsky.social · 11/03/2025
The two postdoctoral positions remain open! (the PhD position has been filled) Applications from deep learning researchers or atmospheric scientists are welcome! Ping me if you have any questions!
0127
François Rozet @francois-rozet.bsky.social · 07/03/2025
🔥 Azula 0.3.0 is out with many new features, including new super fast samplers (LMS, DPM-Solver), new guidance methods (DPS, MMPS) and new plugins (VDM, EMD, EMD2). Check it out!
162
François Rozet @francois-rozet.bsky.social · 15/02/2025
For anyone interested in trying a higher-order optimizer, here is a clean and fast implementation of SOAP 🧼 in PyTorch, with support for low-precision. I recommend using the same learning rate as you would for AdamW. gist.github.com/francois-roz...
gist.github.com
A clean and fast implementation of SOAP in PyTorch
A clean and fast implementation of SOAP in PyTorch - savon.py
081
Reposted by François Rozet
Arnaud Doucet @arnauddoucet.bsky.social · 15/12/2024
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...
drive.google.com
BreimanLectureNeurIPS2024_Doucet.pdf
932868
François Rozet @francois-rozet.bsky.social · 24/01/2025
The template for this poster is now available on GitHub! github.com/francois-roz...
github.com
GitHub - francois-rozet/postr: A minimal poster template in Typst.
A minimal poster template in Typst. Contribute to francois-rozet/postr development by creating an account on GitHub.
3112
Reposted by François Rozet
Gilles Louppe @glouppe.bsky.social · 30/12/2024
📣 Hiring! I am looking for PhD/postdoc candidates to work on foundation models for science at @ULiege, with a special focus on weather and climate systems. 🌏 Three positions are open around deep learning, physics-informed FMs and inverse problems with FMs.
47934
François Rozet @francois-rozet.bsky.social · 15/12/2024
My favourite talk of NeurIPS 2024!
090
Reposted by François Rozet
Matthias Pirlet @mapirlet.bsky.social · 11/12/2024
Great to see such engagement with your poster!
071
Reposted by François Rozet
ruiqigao.bsky.social @ruiqigao.bsky.social · 02/12/2024
A common question nowadays: Which is better, diffusion or flow matching? 🤔 Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.
625459
François Rozet @francois-rozet.bsky.social · 07/12/2024
I'll be in Vancouver from Dec 9 to Dec 16 to present our work at NeurIPS 2024 🇨🇦 If you want to talk about generative models, ML for science, open-source software, or bouldering, send me a DM, a comment or an email!
0244
Reposted by François Rozet
Ruben Ohana @rubenohana.bsky.social · 02/12/2024
Generating cat videos is nice, but what if you could tackle real scientific problems with the same methods? 🧪🌌 Introducing The Well: 16 datasets (15TB) for Machine Learning, from astrophysics to fluid dynamics and biology. 🐙: github.com/PolymathicAI... 📜: openreview.net/pdf?id=00Sx5...
36419
François Rozet @francois-rozet.bsky.social · 02/12/2024
Deep learning can do more than generating cute cat pictures. It is a game changer for Science as a whole. But benchmarking DL methods on scientific data is complex ... until today! I am super proud to have contributed to The Well as part of my internship at @polymathicai.bsky.social !
0224
Reposted by François Rozet
PolymathicAI @polymathicai.bsky.social · 18/11/2024
Hello World!
4274
Reposted by François Rozet
Willie Neiswanger @willieneis.bsky.social · 10/11/2024
I'm making a list of AI for Science researchers on bluesky — let me know if I missed you / if you'd like to join! go.bsky.app/AcP9Lix
16225389
François Rozet @francois-rozet.bsky.social · 15/11/2024
i just love @typst.app
070