Sebastian

Post-Doc at TU Munich, PhD in Artificial Intelligence.
Working on diffusion samplers.

[Sebastian @SebSanokowski]

Learning to remove noise from images yields fantastic image generators. Here's how you can use diffusion models to solve Combinatorial Optimization problems by removing noise from solutions that you don't even have! To be presented @ICML 2024, 🧵👇

[Lorenz Richter @lorenz_richter]

Presenting our spotlight paper on trust regions for optimal control at NeurIPS, https://t.co/YS1VkDYBEB. We show that KL-equipspaced measure transport can be interpreted as geometric annealing with adaptive step sizes, leading to major performance gains on hard control problems.

[Sebastian @SebSanokowski]

Links:
https://t.co/gnEdBVTstw
https://t.co/ffw27E05p6

[Sebastian @SebSanokowski]

Ever experienced instabilities when using the popular LV (Log Variance) loss for training Diffusion Bridge Samplers?

[Sebastian @SebSanokowski]

If you’re at NeurIPS in San Diego next week, we’d love to connect and discuss our work.
Joint work with:
@lugruber0, Christoph Bartmann, @HochreiterSepp, @sebaLeh

[Maximilian Beck @maxmbeck]

🚀 Excited to share our new paper on scaling laws for xLSTMs vs. Transformers.
Key result: xLSTM models Pareto-dominate Transformers in cross-entropy loss.
- At fixed FLOP budgets → xLSTMs perform better
- At fixed validation loss → xLSTMs need fewer FLOPs

🧵 Details in thread

[Differentiable Learning of Comb. Algorithms @diffcoalg]

🔥 New workshop at @NeurIPSConf!
DiffCoALG bridges the gap between classic algorithms & differentiable learning.
Think: LLM reasoning, routing, SAT, MIP — neurally optimized end-to-end.
📌 Submit by Aug 22!
🔗 https://t.co/OiKDhVcaSo
#NeurIPS2025

[Johannes Brandstetter @jo_brandstetter]

General relativity 🤝 neural fields

This simulation of a black hole is coming from our neural networks 🚀

We introduce Einstein Fields, a compact NN representation for 4D numerical relativity. EinFields are designed to handle the tensorial properties of GR and its derivatives.

[Korbinian Poeppel @KorbiPoeppel]

Ever wondered how linear RNNs like #mLSTM (#xLSTM) or #Mamba can be extended to multiple dimensions?
Check out "pLSTM: parallelizable Linear Source Transition Mark networks". #pLSTM works on sequences, images, (directed acyclic) graphs.
Paper link: https://t.co/nU7626uHWK

[Andreas Auer @AndAuer]

We’re excited to introduce TiRex — a pre-trained time series forecasting model based on an xLSTM architecture.

[Günter Klambauer @gklambauer]

Recommended read for the weekend: Sepp Hochreiter's book on AI!

Lots of fun anecdotes and easily accessible basics on AI!

https://t.co/21dJ3xCJ6o

[Florian @fses91]

Happy to introduce 🔥LaM-SLidE🔥!

We show how trajectories of spatial dynamical systems can be modeled in latent space by

--> leveraging IDENTIFIERS.

📚Paper: https://t.co/6s3zIhXJ5o
💻Code: https://t.co/b6LePjMgIb
📝Blog: https://t.co/V1Mtmu4jqn
1/n

[Sebastian @SebSanokowski]

11/11 This is joint work with @willberghammer, @haoyu_wang66, @EnnemoserMartin, @HochreiterSepp, and @sebaleh. See you at #ICLR!
[Poster Link](https://t.co/ZvmE8wIGKc)
[Paper Link](https://t.co/cuiVvNALnq)
---

[Sebastian @SebSanokowski]

1/11 Excited to present our latest work "Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics" at #ICLR2025 on Fri 25 Apr at 10 am!
#CombinatorialOptimization #StatisticalPhysics #DiffusionModels

[Sebastian @SebSanokowski]

10/11 🏆 Our method outperforms autoregressive approaches on Ising model benchmarks and opens new avenues for applying diffusion models to a wide range of scientific applications in discrete domains.