Marcin Sendera

PhD with distinction in probabilistic deep learning @JagiellonskiUni. AI Research Scientist. Diffusion, AI4Science, GFlowNets, AI Safety. @Mila_Quebec alumni.

[Marcin Sendera @MarcinSendera]

1/ Two and a half weeks ago I defended my PhD at the @JagiellonskiUni in Kraków!

"Probabilistic deep learning: from efficient sampling to principled generation" - awarded with distinction. 🎓

Nine papers, three themes, one journey. Quick thread on what was inside 🧵

[Julius Berner @julberner]

Neural samplers for unnormalized densities have come a long way!

A year ago, sampling from a 2,500-D Gaussian mixture density with 20 random modes seemed to be completely out of reach without severe mode collapse.

Today, this is possible with Bridge Matching Samplers (an extension of stochastic interpolants to the data-free setting). Check out our poster at #ICML2026 to learn more! 👇

[Lorenz Richter @ICML 2026 @lorenz_richter]

We present the Bridge Matching Sampler at ICML today (5pm, #3311), a version of stochastic interpolants that does not need data from the target, but only a density. We iterate reciprocal and Markovian projections and employ a fixed-point iteration, see https://t.co/bU4VxJy3VG.

[Lorenz Richter @ICML 2026 @lorenz_richter]

I just arrived in Seoul for #ICML, presenting three works on diffusion-based sampling:

Bridge Matching Sampler: https://t.co/bU4VxJy3VG
Tensor Train Diffusion: https://t.co/zwinbqCc07
Discrete/continuous time equivalences: https://t.co/CtPpH5I783

Write me if you want to meet.

[Marcin Sendera @MarcinSendera]

@ddjrym Oh, you are Dave and the method is also Dave, I see a pattern here 🤯

[Marcin Sendera @MarcinSendera]

@ddjrym @maciejpioro Not even the Spodek, the only place which might be enough is the Convention Centre in Katowice for ~10k ppl, eventually any worse options like Targi Poznańskie

[Stanisław Jastrzębski @kudkudakpl]

For the last months, we’ve been working at @MoleculeOne with @OpenAI on something that felt like a glimpse of the future of science.

Together with @OpenAI , we achieved what we believe is the first near-autonomous discovery in organic chemistry.

https://t.co/YcPzq0Cm8e

🧵

[ML in PL @MLinPL]

You write a book called "Deep Generative Modeling" in 2022. Two years later, generative AI is on the front page of every business publication. That kind of timing is either luck or you were paying close attention before it was obvious.

With Jakub, it's the latter.

He has spent over 15 years working on generative models: variational autoencoders, normalizing flows, diffusion — the actual mechanics of how machines learn to model distributions, not the downstream products that get the press coverage. Over 50 publications at NeurIPS, ICML, ICLR, CVPR, ICCV. In 2024 he served as Program Chair of NeurIPS, which means he was responsible for the scientific quality of one of the biggest venues in the field while several thousand researchers argued with him about reviewer scores.

He has also advised eBay, Qualcomm, and multiple startups, which is a polite way of saying his research has had to hold up outside seminar rooms too.

Currently at the Chan Zuckerberg Initiative. Founder of Amsterdam AI Solutions. Head AI advisor at NatInLab. Three patents.

Jakub Tomczak joins the 10th edition of ML in PL Conference in Warsaw.

[Marcin Sendera @MarcinSendera]

@NxtJust @JagiellonskiUni @NeurIPSConf @TmlrOrg @UncertaintyInAI @ArnaudDoucet1 @AmosStorkey @PiotrRMilos @Yoshua_Bengio @Mila_Quebec @GMUMJU @MLinPL Będę uważał ;)

[Marcin Sendera @MarcinSendera]

1/ Two and a half weeks ago I defended my PhD at the @JagiellonskiUni in Kraków!

"Probabilistic deep learning: from efficient sampling to principled generation" - awarded with distinction. 🎓

Nine papers, three themes, one journey. Quick thread on what was inside 🧵

[Marcin Sendera @MarcinSendera]

@Matigappag @JagiellonskiUni Thanks!

[Marcin Sendera @MarcinSendera]

@AWodeham @JagiellonskiUni Dziękuję :)!

[Marcin Sendera @MarcinSendera]

@langer_han @JagiellonskiUni @NeurIPSConf @TmlrOrg @UncertaintyInAI @ArnaudDoucet1 @AmosStorkey @PiotrRMilos @Yoshua_Bengio @Mila_Quebec @GMUMJU @MLinPL Many thanks Tanmoy!!!

[Marcin Sendera @MarcinSendera]

@JagiellonskiUni @NeurIPSConf @TmlrOrg @UncertaintyInAI @ArnaudDoucet1 @AmosStorkey @PiotrRMilos @Yoshua_Bengio @Mila_Quebec @GMUMJU @MLinPL 12/
Always happy to chat about probabilistic methods, diffusion samplers, GFlowNets, AI for Science, or research more broadly!

🔗 Thesis & full bio: https://t.co/hvMe1vR0EB

Onward 🚀

[Marcin Sendera @MarcinSendera]

@JagiellonskiUni @NeurIPSConf @TmlrOrg @UncertaintyInAI @ArnaudDoucet1 @AmosStorkey @PiotrRMilos @Yoshua_Bengio @Mila_Quebec @GMUMJU @MLinPL 11/
Currently at @JagiellonskiUni and NASK - National Research Institute on AI Safety: agentic red-teaming, reasoning models, probabilistic alignment.