Jakub M. Tomczak

Followed by @jmtomczak.bsky.social on mixtures models and probabilistic circuits!

Now, the fantastic @jmtomczak.bsky.social is telling us about probabilistic circuits at GeMSS/Statlearn 2025 @gemssai.bsky.social

Here we go: @pamattei.bsky.social is kicking off the first lecture of GeMSS/Starlearn 2025! @gemssai.bsky.social @jmtomczak.bsky.social

Shar, you are simply amazing! And working you with is a highlight!

@neuripsconf.bsky.social Program Chair spotted 😁😁

@jmtomczak.bsky.social Jakub, seeing you work towards making NeurIPS happen, has been awe inspiring. What a mammoth effort!

A proud advisee moment 🥹

If you don't know what to read, there you go: link.springer.com/book/10.1007...
I heard from the source that it was the 2nd best selling book in October among thousands of Springer books!

Achieving your goals is impossible without being part of a great team! It feels amazing to be in front of thousands of researchers at @NeurIPSConf, knowing there are outstanding people who have your back.

I'm on my way to #Neurips 2024, the largest AI conference in the world, where I have the privilege of being the Program Chair along amazing Danielle Belgrave, Ulrich Paquet, Angela Fan and Cheng Zhang! If you want to chat about #GenAI (not only LLMs or Diffusion), pls let me know.

That's simply awesome, Kyle! We provide code, so if you get any results, please ping me 🙏

Thank you, Durk! We didn't reproduce CR-NVAE due to lack of resources. However, their regularization technique (CR) is actually applicable to almost any VAE. Maybe CR-VampPrior 2.0 might get even better 🤩

I am super hyped and happy with our recent paper on a ✨VampPrior 2.0✨: Hierarchical VAE with a diffusion-based VampPrior! 🦇 We got SOTA VAE results on CIFAR-10! Kudos to Anna Kuzina because this TMLR paper is the last chapter in her PhD thesis 🤩
📃 tinyurl.com/22rvzc4f
💻 github.com/AKuzina/dvp_...

Test of Time Paper Awards are out! 2014 was a wonderful year with lots of amazing papers. That's why, we decided to highlight two papers: GANs (@ian-goodfellow.bsky.social et al.) and Seq2Seq (Sutskever et al.). Both papers will be presented in person 😍

Link: blog.neurips.cc/2024/11/27/a...

(I'm still figuring out how 🦋 works, so please be patient with my potential mistakes 🙈)

I've created a startepack on Generative Modeling: go.bsky.app/Hd9ykTw

Lovely! Thanks for creating it 🙌

Thank you, @nolovedeeplearning.bsky.social 🙌