Joined November 2021
- Tweets 74
- Following 142
- Followers 214
- Likes 650
11 Photos and videos
Pinned Tweet
5 Jun 2024
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, 🧵👇
3
56
210
54,474
Sebastian retweeted
3 Dec 2025
Presenting our spotlight paper on trust regions for optimal control at NeurIPS, arxiv.org/pdf/2508.12511. 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.
3
20
120
6,974
28 Nov 2025
Ever experienced instabilities when using the popular LV (Log Variance) loss for training Diffusion Bridge Samplers?
1
6
18
10,592
28 Nov 2025
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
1
1
3
212
28 Nov 2025
1
3
155
Sebastian retweeted
3 Oct 2025
🚀 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
14
41
231
84,866
Sebastian retweeted
🔥 New workshop at @NeurIPSConf!
DiffCoALG bridges the gap between classic algorithms & differentiable learning.
Think: LLM reasoning, routing, SAT, MIP — neurally optimized end-to-end.
đź“Ś Submit by Aug 22!
🔗 sites.google.com/view/diffco…
#NeurIPS2025
6
12
3,111
Sebastian retweeted
17 Jul 2025
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.
11
73
321
39,337
Sebastian retweeted
16 Jun 2025
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: arxiv.org/abs/2506.11997
4
42
135
15,126
Sebastian retweeted
2 Jun 2025
We’re excited to introduce TiRex — a pre-trained time series forecasting model based on an xLSTM architecture.
5
21
70
14,851
Sebastian retweeted
30 May 2025
Recommended read for the weekend: Sepp Hochreiter's book on AI!
Lots of fun anecdotes and easily accessible basics on AI!
beneventopublishing.com/ecow…
2
4
18
1,526
Happy to introduce 🔥LaM-SLidE🔥!
We show how trajectories of spatial dynamical systems can be modeled in latent space by
--> leveraging IDENTIFIERS.
đź“šPaper: arxiv.org/abs/2502.12128
đź’»Code: github.com/ml-jku/LaM-SLidE
đź“ťBlog: ml-jku.github.io/LaM-SLidE/
1/n
1
19
34
3,021
24 Apr 2025
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
1
15
22
1,760
24 Apr 2025
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.
1
1
87
24 Apr 2025
11/11 This is joint work with @willberghammer, @haoyu_wang66, @EnnemoserMartin, @HochreiterSepp, and @sebaleh. See you at #ICLR!
[Poster Link](iclr.cc/virtual/2025/poster/…)
[Paper Link](arxiv.org/abs/2502.08696)
---
2
107