François Rozet
@francois-rozet.bsky.social
datamancer, generative models, bayesian inference, dynamical systems, open-source software, phd with @glouppe.bsky.social
Reposted by François Rozet
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 🌱)
November 27, 2025 at 1:37 PM
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 🌱)
Reposted by François Rozet
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.
October 24, 2025 at 12:38 PM
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.
Reposted by François Rozet
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 ⤵️
October 24, 2025 at 12:38 PM
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 ⤵️
Reposted by François Rozet
🚀 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...
Check the repo and the complete wiki!
github.com/montefiore-s...
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
github.com
October 8, 2025 at 10:33 AM
🚀 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...
Check the repo and the complete wiki!
github.com/montefiore-s...
Reposted by François Rozet
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
October 3, 2025 at 4:14 PM
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...
Reposted by François Rozet
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 🤗
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 🤗
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
media.tenor.com
September 23, 2025 at 1:00 PM
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 🤗
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 🤗
Reposted by François Rozet
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!
Congratulations to six of our #researchers, including Lukas Heinrich, who receive prestigious ERC #StartingGrants worth up to 1.5 million euros each for projects in #informatics, #medicine, #LifeSciences & #NaturalSciences: go.tum.de/682017 👏
#ERCStG @erc.europa.eu
📷A.Eckert
#ERCStG @erc.europa.eu
📷A.Eckert
Six ERC Starting Grants for researchers at TUM
Six further researchers at TUM are to receive the prestigious ERC Starting Grants for their projects.
go.tum.de
September 4, 2025 at 10:45 AM
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!
Reposted by François Rozet
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!
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 👇
We got lost in latent space. Join us 👇
September 3, 2025 at 2:01 PM
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!
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 👇
We got lost in latent space. Join us 👇
September 3, 2025 at 1:40 PM
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 👇
We got lost in latent space. Join us 👇
@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...
July 26, 2025 at 9:50 AM
@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...
Reposted by François Rozet
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...
📝 Paper: hdl.handle.net/2268/326874
💻 Blog: damien-ernst.be/2025/06/10/a...
July 16, 2025 at 2:32 PM
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...
📝 Paper: hdl.handle.net/2268/326874
💻 Blog: damien-ernst.be/2025/06/10/a...
Reposted by François Rozet
🎉 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
Keep an eye out for updates on deadlines etc, we will be updating the website soon
ml4physicalsciences.github.io
#ML4PS2025
July 10, 2025 at 3:09 PM
🎉 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
Keep an eye out for updates on deadlines etc, we will be updating the website soon
ml4physicalsciences.github.io
#ML4PS2025
Reposted by François Rozet
As always, a very nice talk from Francois Lanusse: Generative Al for Inverse Problems and Forecasting
Slides: eiffl.github.io/talks/Paris2...
Slides: eiffl.github.io/talks/Paris2...
July 3, 2025 at 4:23 PM
As always, a very nice talk from Francois Lanusse: Generative Al for Inverse Problems and Forecasting
Slides: eiffl.github.io/talks/Paris2...
Slides: eiffl.github.io/talks/Paris2...
Reposted by François Rozet
🏹 Job alert: PhD/postdoc positions in Scientific Foundation Models at the University of Liège (Belgium)
📍 Liège 🇧🇪
🔗 More info: https://bit.ly/43SJtUG
📍 Liège 🇧🇪
🔗 More info: https://bit.ly/43SJtUG
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...
bit.ly
June 12, 2025 at 9:00 AM
🏹 Job alert: PhD/postdoc positions in Scientific Foundation Models at the University of Liège (Belgium)
📍 Liège 🇧🇪
🔗 More info: https://bit.ly/43SJtUG
📍 Liège 🇧🇪
🔗 More info: https://bit.ly/43SJtUG
Reposted by François Rozet
📝 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.
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.
June 9, 2025 at 2:43 PM
Reposted by François Rozet
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!
📣 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.
June 4, 2025 at 12:24 PM
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!
Reposted by François Rozet
📣 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/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 ⬇️
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...
arxiv.org
June 2, 2025 at 11:18 AM
📣 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/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 ⬇️
Reposted by François Rozet
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
📢 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 🔁
May 23, 2025 at 11:57 AM
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
📢 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 🔁
May 23, 2025 at 11:07 AM
📢 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 🔁
Reposted by François Rozet
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...
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 - 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
github.com
May 14, 2025 at 6:20 PM
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...
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...
Reposted by François Rozet
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.)
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.)
May 13, 2025 at 5:00 PM
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.)
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.)
Reposted by François Rozet
<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 🧵
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 🧵
April 29, 2025 at 4:48 AM
<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 🧵
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 🧵
Reposted by François Rozet
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
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
April 16, 2025 at 9:20 AM
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
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
Reposted by François Rozet
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...
I just released a small library to easily implement and use causal-flows:
github.com/adrianjav/ca...
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
github.com
February 13, 2025 at 5:54 PM
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...
I just released a small library to easily implement and use causal-flows:
github.com/adrianjav/ca...
Reposted by François Rozet
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)
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 ...
docs.google.com
March 30, 2025 at 6:04 PM
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)