For the first time, we can directly link state-discrete continuous-time diffusion models to their time- and space-continuous (SDE-based) counterparts, i.e. score-based generative modeling. Credits go to the Ehrenfest process (+ ludiXIVwinkler & Manfred): arxiv.org/pdf/2405.03549

I gave a presentation on our latest diffusion-based sampling work virtually at The Alan Turing Institute yesterday. The work has been mostly done jointly with Julius Berner and Nik Nüsken. You can find the recording here: youtube.com/watch?v=-A7IRw…

I will give at talk about our latest work on PINN-based sampling from densities via SDEs and ODEs (with Julius Berner and Jingtong (Jeff) Sun) at the Fields Institute in Toronto today. Check out the paper at arxiv.org/pdf/2407.07873

I gave a talk on our latest work on the connections between dynamical systems, PDEs, control and path space measures for sampling from densities at the The Fields Institute in Toronto last week (with Julius Berner, Jingtong (Jeff) Sun). You can find the recording here: youtube.com/watch?v=ue8liZ…

And back to Vienna again. I will present our work on time-continuous discrete-space diffusion models at ICML Conference (with ludiXIVwinkler, Thu, 11:30). For the first time, we can connect those models to score-based generative modeling, see openreview.net/pdf?id=8GYclcx…. Ping me!

Our work from last year on solving high-dimensional PDEs with tensor trains via robust BSDE-based methods has just appeared in Journal of Machine Learning Research. It's a follow-up of proceedings.mlr.press/v139/richter21… and suggests a new loss that is robust and explicit, i.e. fast.

Check out our new paper on diffusion-based sampling, combining diffusion models with Sequential Monte Carlo in a principled way, arxiv.org/pdf/2412.07081. It improves sampling quality and leads to more robust training. Thanks Junhua Chen, Julius Berner, Denis Blessing for the great work!

Also on open/close peer review, I analyzed the AI/ML community's interest by analyzing user activity on open statistics across different venues in the past year. The user activity pattern shows (in the figure) that the fully open peer review venue, ICLR, receives significantly

My friend pan tom is looking for interns working on generative modeling for proteins. Let him know in case you are interested.

Our new work arxiv.org/pdf/2503.01006 extends the theory of diffusion bridges to degenerate noise settings, including underdamped Langevin dynamics (with Denis Blessing, Julius Berner). This enables more efficient diffusion-based sampling with substantially fewer discretization steps.