⁦Pascal Notin⁩ kicks off the first talk of GenLife 2024! genlife.dk

Application deadline is approaching (April 30th): We are looking for two postdocs in Generative Modelling at DTU Compute: one within physical systems (w/ @rasbjo) and one within life science (w/ mlls.dk). efzu.fa.em2.oraclecloud.com/hcmUI/Candidat… Please RT.

Heyo, I’m starting a stay at the University of Cambridge. If anyone around wants to connect, shoot me a message !

We seek a postdoc (2-yr) at DTU specialising in generative modelling. Focus on diffusion & score-based models applied to physical systems. Interested? Contact me or learn more: groups.google.com/g/ml-news/c/p7… Check out our ongoing work: arxiv.org/abs/2405.05981 Please RT! #Postdoc

Excited to share that our paper on reducing variance in diffusion models with control variates is published at the SPIGM ICML Conference workshop. Come check it out! Thanks a lot to will grathwohl Jes Frellsen @carlhenrikek Michael Riis for the collaboration! openreview.net/pdf?id=YqFIzHA…

Landed in Vienna for icml ! Reach out if you want to chat or grab a (specialty) coffee

"A tutorial on automatic differentiation with complex numbers" (by Nicholas Krämer): arxiv.org/abs/2409.06752

Ever thought about using matrix-exp's or log-det's in large-scale ML (think PDEs/GGN matrices with >1M rows)? I have, and maybe you have, too—but gradients? That's where it gets tricky. Not anymore! We have a #NeurIPS2024 spotlight: "Gradients of Functions of Large Matrices."🧵

diffusion models are just a ploy by CS PhDs to get their departments to pay for them to learn stochastic calculus so that they can get finance jobs

Heading to Vancouver for NeurIPS to present our paper “On Conditional Diffusion Models for PDE Simulation”. I'll be together with Sasha and Cristiana Diaconu at poster 2500 during Thursday’s late afternoon session. Looking forward exciting discussions and meeting new people!

🛩️ On my way to #NeurIPS2024 and excited to chat about (ML applications of) linear algebra, differentiable programming, and probabilistic numerics! Feel free to DM if you’d like to meet up, hang out, and/or discuss any of these topics 😊

Poster session happening *today* at 4:30 local time. *East* Exhibit Hall. Poster #3511. Looking forward to presenting this work! See you there? 🙂

Honored to receive the Jorck's Fund Research Award (DKK450,000) for my research and teaching in generative AI given at the Danish Supreme Court! 🎉 Grateful for the incredible support of my PhD students, postdocs, collaborators and family. 🙏 Details: dtu.dk/english/news/n…

Tweeting again about sampling, my favourite 2024 Monte Carlo paper is arxiv.org/abs/2307.01050 by F. Vargas, Shreyas Padhy, D. Blessing & N. Nüsken: . Propose a "simple" loss to learn the drift you need to add to Langevin to follow a fixed probability path.

We have a new cool preprint with Cheuk Kit Lee. We developed a sweet Sequential Monte Carlo algorithm for unbiased samples from a tempered distribution p(x0)p(y|x0)^α and applied it to discrete diffusion for text arxiv.org/abs/2502.06079. Huge thanks to Francisco Vargas Michael Albergo

Heading to ICLR 2026 2025 tomorrow in Singapore! I’ll be giving a talk at the FPI workshop on our most recent work with Cheuk Kit Lee . Hit me up if you want to chat, or have some good coffee ! arxiv.org/pdf/2502.06079

Francisco Vargas and Michael Albergo with a combined talk on sampling inference and transport at #FPIworkshop.

Finally tried those apollo bagels

Heading to Microsoft Research over the summer to intern and work on some cool diffusion stuff 🫶🏽 hit me up if you want to grab a coffee

[1/9]🚀Excited to share our new work, RNE! A plug-and-play framework for everything about diffusion model density and control: density estimation, inference-time control & scaling, energy regularisation. More details👇 Joint work with Jose Miguel Hernández-Lobato Yuanqi Du, Francisco Vargas