At #ICML2025 this week? Come check out our work on controlled generation, simulation-free latent SDEs, and risk monitoring in test-time adaptation, and chat with the awesome students that made it happen! #SDE #Diffusion #FlowMatching #TTA #UncertaintyQuantification

🚨🚀 Come hear @gbarto.bsky.social talk about SDE Matching tomorrow! SDE Matching is a highly efficient and scalable training framework for Latent/Neural SDEs. You no longer have to discretize or simulate your SDE models when fitting them to data. #SDE #Diffusion #FlowMatching #ML

Overleaf down 😅 #Overleaf #NeurIPS

Wow, I am floored! With the UAI results in, my lab with collaborators have achieved the #PerfectGame 🏆 100% acceptance rate across an entire #ML cycle! (5/5 #NeurIPS, #ICLR, 2/2 #AISTATS, 2/2 #ICML, 1/1 #UAI) 10 for 10. 🥳🍾🤩 #Science #AI #ElementalAI

Exciting news: AMLab is happy to have 7 papers accepted at #ICML2025! 🎉 See the thread below for the full list 📝 and meet us in Vancouver to discuss them further! 🇨🇦 🧵1 / 8

#AISTATS2025 happening in Phuket, Thailand! I have two papers at the conference: 1. Max-Rank: Efficient Multiple Testing for Conformal Prediction 2. Variational Combinatorial Sequential Monte Carlo for Bayesian Phylogenetics in Hyperbolic Space Both at poster session 2!

Very excited that our work (together with my PhD student @gbarto.bsky.social and our collaborator Dmitry Vetrov) was recognized with a Best Paper Award at #AABI2025! #ML #SDE #Diffusion #GenAI 🤖🧠

If you missed it and are attending #AABI at NTU today you can find me presenting it again at the afternoon poster session! approximateinference.org

Come check out SDE Matching at the #ICLR2025 workshops, a new simulation-free framework for training fully general Latent/Neural SDEs (generalisation of diffusion and bridge models). FPI: Morning poster session DeLTa: Afternoon poster session #SDE #Bayes #GenAI #Diffusion #Flow

The calm before the storm #ICLR2025 🔥🔥🔥

Attending #ICLR2025 and #AABI2025. Presenting at the conference and workshops: 1. E-Valuating Classifier Two-Sample Tests, Friday, Hall 3 + Hall 2B #437 2. SDE Matching, Sunday-Tuesday, FPI/DeLTa/AABI openreview.net/forum?id=dwF... arxiv.org/abs/2502.02472 lmk if you want to chat!

New blog post: let's talk about latents! sander.ai/2025/04/15/l...

Working on probabilistic modeling, inference, and decision-making? Join us at #AABI 2025 if you’re going to Singapore later this month! Register here (free but spots are limited!): approximateinference.org

Make sure to get your tickets to AABI if you are in Singapore on April 29 (just after #ICLR2025) and interested in probabilistic modeling, inference, and decision-making! Tickets (free but limited!): lu.ma/5syzr79m More info: approximateinference.org #Bayes #MachineLearning #ICLR2025 #AABI2025

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)

Don't forget to submit your Fast-Track papers to #AABI2025 today! If you have an accepted paper in machine learning since AABI 2024 present it as a poster. CfP: approximateinference.org/call/ Looking forward to seeing everyone in Singapore on April 29, just after #ICLR2025!

A bit unfortunate that AC_CONF_LIST doesn't include AISTATS or UAI...

I already advertised for this document when I posted it on arXiv, and later when it was published. This week, with the agreement of the publisher, I uploaded the published version on arXiv. Less typos, more references and additional sections including PAC-Bayes Bernstein. arxiv.org/abs/2110.11216

This is really interesting! Learning the posterior probability path p(x0 | xt) rather than only the mean is something we suggested in Variational Flow Matching as well, but for a different reason (generating discrete data). Very cool that it can also be used for faster generation.

You still have a chance to submit your work to all tracks for AABI. New deadline is February 14 for both Workshop and Proceedings track! #AABI2025 #ML #ICLR2025 #Stats #Bayes

We have extended the #AABI workshop and proceedings deadlines! *New deadlines:* Workshop Track: February 14, AoE Proceedings Track: February 14, AoE approximateinference.org/call/ #ProbML #AABI #ICLR #Bayes

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

Submit your work to the 7th Symposium on Advances in Approximate Bayesian Inference! #AABI This year, #AABI will be co-located with #ICLR2025! Workshop Track: February 7, AoE Proceedings Track: February 7, AoE Fast Track: February 18 / March 14, AoE approximateinference.org/call/

Don't forget #AABI, the Symposium on Advances in Approximate Bayesian Inference is coming to Singapore!! Co-located #ICLR2025 Workshop Track: February 7, AoE Proceedings Track: February 7, AoE Fast Track: February 18 / March 14, AoE approximateinference.org/call/ #ML #Bayes #GenAI

📢PSA: #NeurIPS2024 recordings are now publicly available! The workshops always have tons of interesting things on at once, so the FOMO is real😵‍💫 Luckily it's all recorded, so I've been catching up on what I missed. Thread below with some personal highlights🧵

Interesting 🤔 Reminds me of our work on combining multi-proposals with "multi-chains". This worked best by splitting compute at 50/50 between the number of (interacting) Markov chains and independent proposals. proceedings.mlr.press/v48/rainfort...

#AISTATS decisions are out! My lab went 2 for 2 😀 I would also recommend having a look at submitting to the AABI fast-track or workshop track that happens in-between ICLR and AISTATS in Singapore: approximateinference.org

Eagerly waiting for #ICLR2025 or #AISTATS2025 results? Are you working on probabilistic #ML, #GenAI, approximate methods, or #UQ? Then check out #AABI held on Apr 29 co-located with #ICLR2025 + Fast-Track for accepted ICLR/AISTATS submissions -> approximateinference.org

The ELLIS Pre-NeurIPS Fest 2024 was a big success! 🎉 Thousands attended & hundreds of posters were showcased across 17 ELLIS Sites. A great platform for ELLIS researchers to connect with #AI & #ML enthusiasts. Thanks to all participating Sites! 👏 #ELLISforEurope #NeurIPS2024

One #postdoc position is still available at the National University of Singapore (NUS) to work on sampling, high-dimensional data-assimilation, and diffusion/flow models. Applications are open until the end of January. Details: alexxthiery.github.io/jobs/2024_di...

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...

Today is Lucia, not really celebrated much outside Sweden. But it's a fun tradition with lots of candles, song, snacks, glögg, etc. For now here is a pic with Christmas tree 🎄 at work #Lab42 #NeuralNetworks #ML

Come talk to @zmheiko.bsky.social about his work on sample-efficient black box variational inference! (East Exhibition Hall #4105)

François Cornet and @gbarto are presenting their work on Equivariant Neural Diffusion now at East Exhibition #2403!

Here are the dapper @metodjazbec.bsky.social and Alexander Timans, presenting their work on early-exit with risk control.

Check out this work from my group that @gbarto.bsky.social will present later today! Diffusion (bridges)/flows with learnable probability paths (simulation-free!) that can make your generative model better (SOTA CIFAR-10 and ImageNet) and faster!

Today my collaborators are presenting no less than 3 of our papers at #NeurIPS2024 Come check out the posters and talk to everyone to find out more about molecule generation, early-exit with risk control, or speeding up variational inference!

Every year at NeurIPS, I get a sense of where the community is headed. I'm so happy that the era of larger language models on larger datasets is coming to an end.

When a bunch of diffusers sit down and talk shop, their flow cannot be matched😎 It's time for the #NeurIPS2024 diffusion circle! 🕒Join us at 3PM on Friday December 13. We'll meet near this thing, and venture out from there and find a good spot to sit. Tell your friends!

This is happening today! Unfortunately I couldn't be there, but go talk to @eijkelboomfloor.bsky.social @gbarto.bsky.social @jwvdm.bsky.social about our work on Variational Flow Matching.

🪪VISA: Variational Inference with Sequential Sample-Average Approximations by @zmheiko.bsky.social, @canaesseth.bsky.social, @jwvdm.bsky.social 🪪https://neurips.cc/virtual/2024/poster/93819 📜https://arxiv.org/abs/2403.09429 🧵8 / 12

🚪Fast yet Safe: Early-Exiting with Risk Control by @metodjazbec.bsky.social*, Alexander Timans*, Tin Hadži Veljković, Kaspar Sakmann, Dan Zhang, @canaesseth.bsky.social, Eric Nalisnick 🪪https://neurips.cc/virtual/2024/poster/94477 📜https://arxiv.org/abs/2405.20915 🧵6 / 12

🦠Equivariant Neural Diffusion for Molecule Generation by François Cornet, @gbarto.bsky.social, Mikkel Schmidt, @canaesseth.bsky.social 🪪https://neurips.cc/virtual/2024/poster/96702 🧵4 / 12

⚙️Variational Flow Matching for Graph Generation by @eijkelboomfloor.bsky.social *, @gbarto.bsky.social*, @canaesseth.bsky.social, @wellingmax.bsky.social, @jwvdm.bsky.social 🪪https://neurips.cc/virtual/2024/poster/94958 📜https://arxiv.org/abs/2406.04843 🧵3 / 12

🌊Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling by @gbarto.bsky.social , Dmitry Vetrov, @canaesseth.bsky.social 🪪https://neurips.cc/virtual/2024/poster/94656 📜https://arxiv.org/abs/2404.12940 🧵2 / 12

#NeurIPS2024 #ML

Some good reading tips, especially if you're interested in the fundamentals of Monte Carlo methods! #SMC #IS #Sampling #RNG

🐑 Come and check out Variational Flow Matching for Graph Generation next week at @neuripsconf.bsky.social ! 🐑 Wed 11 Dec 11 a.m. PST — 2 p.m. PST West Ballroom A-D #7103 arxiv.org/abs/2406.04843

We are the premier conference on #uncertainty in #AI and #ML since 1985 🧓 Hello, 🦋! Follow us to reduce uncertainty!