Looking for insights into the performance gap between unconditional and conditional diffusion models when the guidance weight is set to 0 👀

New interest: super-resolved images from undertrained flow matching models

lebellig@lebellig.bsky.social · 2w ago

I should keep this checkpoint for later

I should keep this checkpoint for later

So cool that we have mentats to solve all the difficult math problems we can finally spend our free time fighting across sand deserts under a blazing sun.

Meet Charlotte Pelletier, Assoc. Prof at Université Bretagne Sud 🇫🇷 & ELLIS Member. She researches AI, particularly in the scope of time series analysis with applications in remote sensing and Earth observation. Her advice for young scientists focuses on investing in a strong professional network.

🚀 New paper: Balancing Frequencies and Pixels in Flow Matching We tackle the low-frequency bias in pixel-space flow matching and train JiT up to 40% faster without any architectural changes. 📄 Read it here: arxiv.org/abs/2609.02748

We’re excited to release the updated article and code of InSARFlow! 🌊⛵ InSARFlow is a Riemannian flow matching model designed to denoise SAR interferograms while preserving the cyclical nature of phase differences.🌀 📄 Article: hal.science/hal-05710871... 💻 Code: github.com/lebellig/ins...

My lab is looking for an Assistant Research Scientist to work on AI for Climate Science. No Ph.D is required for this position, just a BS and relevant experience. The application deadline is Sept 20. Join me in making better climate models! apply.interfolio.com/191796

Yesterday I watched a movie about an AI4Science researcher who gets angry after having his research grant application rejected (badly explained movie plot). Maybe we should take it as a warning about research funding cuts

We are happy to announce that 28 workshops have been accepted for the Paris event, as part of the 102 accepted NeurIPS workshops: blog.neurips.cc/2026/08/10/a... They will take place on Sat Dec 12 + Sun Dec 13, 2026 (for Paris) The suggested deadline for Workshop submissions is close (Aug 29th)!

🌱 Big news from Climate AI Nordics (CAIN)! We are officially registered as an NGO! 🌍✨ Network members can now become official members with AGM voting rights to help shape our future. Join us or get involved! More info: climateainordics.com/news/2026-08-04-cain-ngo/ 🤖💚

Climate AI Nordics is now an official NGO

Climate AI Nordics becomes an official NGO (ideell förening)

climateainordics.com

Here's the tale of how @jder.bsky.social and I scaled Samudra, a neural ocean emulator capable of predicting 8 years of the ocean on a single GPU, to operate at a full 1/4° resolution (16x the size in bytes). It was quite a humbling process.

Open Athena@openathena.ai · 2mo ago

Simulating ocean climate takes a supercomputer 4,600+ CPU cores to produce 12 simulated years per day (SYPD). Samudra 2 produces 4,800 SYPD on 1 GPU at the same resolution. In a new blog, @al.merose.com reports on Samudra, a neural ocean emulator built in collaboration with NYU & MIT: bit.ly/oa-ss

NeurIPS submissions confirmed to be a heat-loving species. Warmer year, bigger bloom. Every degree we add, the deadline gets denser 🌻 Good news for the field, we're having a really good growing season 👨‍🌾

You can train your image-to-image flow matching model on badly aligned data, you just have to tell it how bad it is. 🫣 Great work from @lebellig.bsky.social and Aimi Okabayashi with cool applications to remote sensing. It's FlowEO 2.0!

lebellig@lebellig.bsky.social · 3mo ago

The last project of my PhD is finally out! 🪴 It was a pleasure collaborating with Aimi on this work! We introduce A²BM: Alignment-Aware Bridge Matching, a new framework for image-to-image translation with weakly aligned image pairs. Paper 📄: arxiv.org/pdf/2607.16294

The last project of my PhD is finally out! 🪴 It was a pleasure collaborating with Aimi on this work! We introduce A²BM: Alignment-Aware Bridge Matching, a new framework for image-to-image translation with weakly aligned image pairs. Paper 📄: arxiv.org/pdf/2607.16294

I organize a 1 day workshop on Generative modelling @ENS Lyon, October 9th Call for oral/poster contributions is open; details at gdr-iasis.cnrs.fr/reunions/mod...

I'd like to announce that at @openathena.ai, @jder.bsky.social and I helped @m2lines.bsky.social release Samudra 2. We scaled this neural ocean emulator to train on 16x the size of data in bytes on the same hardware budget. We can now skillfully predict 8 years of the ocean on a single GPU at a 1/4°

🌊 Samudra 2: A Fast, Cheap AI Ocean Model, Now at the Scale That Matters

M²LInES’ neural ocean emulator now runs multi-year simulations at eddy-permitting resolution on a single GPU, turning a supercomputer-scale…

medium.com

Slides for our ICML tutorial on Memorization and Generalization of Diffusion and Flow Matching Models are now available ! 🌀 memorization-generalization.github.io @quentinbertrand.bsky.social

Heading to #ICML2026 🇰🇷 and interested in diffusion models, flow matching, and their generalization capabilities? Don't miss the excellent tutorial by @mathurinmassias.bsky.social and @quentinbertrand.bsky.social on Monday! 📍 Hall D1 🗓️ Monday, July 6 🕘 9:00–11:30 AM Details: icml.cc/virtual/2026...

Heading to #ICML2026 🇰🇷 and interested in diffusion models, flow matching, and their generalization capabilities? Don't miss the excellent tutorial by @mathurinmassias.bsky.social and @quentinbertrand.bsky.social on Monday! 📍 Hall D1 🗓️ Monday, July 6 🕘 9:00–11:30 AM Details: icml.cc/virtual/2026...

🛰️ Introducing UniverSat: one transformer backbone for Earth Observation that handles ANY sensor, ANY spatial, spectral & temporal resolution, ANY scale — with a single set of weights. 🌍

I took Lyon's rainy days in early May as a warm welcome, now with the heatwave I think my acclimatisation is complete, so it's time to make it official! I've started a postdoc on generative models in Inria's Ockham team working with @mathurinmassias.bsky.social and @quentinbertrand.bsky.social ☀️

We explored the impact of variability sources in generative modeling. Turns out, we've been neglecting the error bars associated with training variability all along! We should aim to report results that we are sure of their scientific validity, instead of seed engineering!

Kyutai@kyutai-labs.bsky.social · 4mo ago

🎰 Welcome to the FID Lottery. We pulled the lever 25 times on the same machine. Identical diffusion model, identical ImageNet class-cond recipe, only the seed changed. The house paid out anywhere from 33.59 to 35.69 FID. A 2.1-point spread, pure luck. Step onto the floor 👇🧵

one anecdote: I was searching for a link to one of my old papers on Google, and the automated Gemini summary attributed all of my lab's work to my husband

Mel Andrews@bayesianboy.bsky.social · 4mo ago

When utilized in literature review, LLMs consistently 1. fail to mention female authors in female-led literatures, 2. insist that men are more influential or more heavily cited when this is contradicted by objective citation counts, and 3. attribute women’s work to hallucinated male scholars.

The alpha version of my new book "Optimal Transport for Machine Learners" is out, with in particular an online version with interactive figures www.gpeyre.com/ot4ml/

🎆 New paper! "Random Process Flow Matching: Generative Implicit Representations of Multivariate Random Fields", by Julien Lalanne, accepted to ICML'26 🥳 We're proposing flow-matching for inpainting in ultra-sparse setup, with applications to seismic interpolation. 📜 arxiv.org/abs/2605.28625 1/

Random Process Flow Matching: Generative Implicit Representations of Multivariate Random Fields

Generative modeling provides a powerful framework for learning data distributions. These models initially relied on probabilistic methods such as Gaussian Processes (GP) for uncertainty-aware predicti...

arxiv.org

"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

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...

arxiv.org

ICML Conference@icmlconf.bsky.social · 5mo ago

Congrats again to authors of accepted #ICML2026 papers! The camera-ready deadline is 5/28. Drawing your attention to two specific features: 1. As last year, to help communicate research to a broad audience, papers will have lay summaries. Tips & details in blog 1/3

Thrilled to share that MIRO is accepted to ICML 2026 @icmlconf.bsky.social ! 🎉 By training on the reward scores, we can simply condition the model on high rewards at inference time to guarantee top-tier, aligned outputs. We’ve updated our paper with some additional results!

MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency

The default paradigm of post-training text-to-image generators includes post-hoc selection of generated images, and subsequent training with one reward model to align the generator to the reward, typi...

arxiv.org

Nicolas Dufour@nicolasdufour.bsky.social · 11mo ago

We introduce MIRO: a new paradigm for T2I model alignment integrating reward conditioning into pretraining, eliminating the need for separate fine-tuning/RL stages. This single-stage approach offers unprecedented efficiency and control. - 19x faster convergence ⚡ - 370x less FLOPS than FLUX-dev 📉

📢 The TerraBytes workshop is returning for a 2nd edition - this time at ECCV 2026. Submit your paper before June 18th and join in Malmö, Sweden! 🔗 terrabytes-workshop.github.io

👏 Folks! If you are curious about the Generative Modeling via Drifting paper, but you find it difficult to understand → I wrote a different interpretation of it. It's called: "An Expectation-Maximization interpretation of Generative Modeling via Drifting" davidpicard.github.io/pdf/An_Expec...