Florian (@fses91) profile picture
Joined February 2017
Photo by Florian (@fses91)Photo by Florian (@fses91)Photo by Florian (@fses91)Photo by Florian (@fses91)Photo by Florian (@fses91)Photo by Florian (@fses91)Photo by Florian (@fses91)Photo by Florian (@fses91)Photo by Florian (@fses91)Photo by 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: arxiv.org/abs/2502.12128 💻Code: github.com/ml-jku/LaM-SLidE 📝Blog: ml-jku.github.io/LaM-SLidE/ 1/n
1
19
2
34
3,136
We just hit 7th out of 5,000+ teams in the ARC-AGI-3 Challenge! 🚀 Biggest takeaway? Under tight compute and memory constraints, a good harness and high inference throughput beat a bigger model! Huge shoutout to the team: @fses91 @MI99835819 @gklambauer kaggle.com/competitions/arc-…
1
4
2
19
1,440
KronLSTM is out!! | Candidate to replace TRANSFORMER in LLMs KronLSTM is built on the Kronecker Delta Rule: instead of correcting the vector stored at a key, it corrects a single scalar, how strongly this key is bound to this value. P: arxiv.org/abs/2610.26834
12
65
7
497
24,770
Everyone wants to have solved a hard problem, but almost nobody wants to live inside the grind of actually solving it. The breakthroughs belong to the few who are obsessed with the process, not just the idea of the outcome
205
474
63
5,002
168,703
G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models Symbolic solver have to branch to check different choices -- recurrent reasoning models ( not LLMs!) can help them to speed up solving. BTW: Frontier AIs fail here! P: arxiv.org/abs/2607.02491
4
23
1
135
8,253
We unlocked the working memory of LLMs 💥 Reasoning in Memory (RiM) replaces autoregressive "thinking out loud" with fixed memory blocks that form a task-specific workspace for latent reasoning. The key idea is simple: reasoning should happen inside the LLM, not in its output!
27
54
10
322
60,155
Symbol-equivariant Recurrent Reasoning Models (SE-RRM) SE-RRM advances HRM and TRM -- guaranteed identical solutions for problems with permuted colors (ARC AGI) or digits (Sudoku). Coolest part: extrapolation to larger problem sizes!!! P: arxiv.org/abs/2603.02193
3
41
1
211
15,675
# AI in Drug discovery just BROKE THROUGH a wall # A newer AI model, ConGLUDe, as fast but much more accurate than DrugCLIP. Instead on just 40K structure-based data, ConGLUDe is trained on 100M datapoints from ligand-based data P: arxiv.org/abs/2601.09693
BIG BREAKTHOUGH: A new AI tool could dramatically speed up the discovery of life saving medicines. Researchers at Tsinghua University created a new system called DrugCLIP, that can screen drug molecules against human proteins at a speed that makes traditional methods look ancient. > DrugCLIP uses deep contrastive learning to turn both molecules and protein binding pockets into vectors and match them almost instantly. > It screened 500 million molecules across 10,000 human proteins, covering half of the entire human druggable proteome. > The system completed 10 trillion molecule protein evaluations in a single day, roughly 10 million times faster than classic docking simulations. > They used AlphaFold2 to generate protein structures and then refined binding pockets with a custom tool called GenPack. > The model even identified compounds for TRIP12, a protein linked to cancer and autism that has resisted traditional drug-targeting approaches. All data and models are open access, so labs worldwide can now speed up early stage drug discovery.
10
59
3
291
26,525
The Great Comeback of Self-Normalizing Networks in 2025: It’s been a wild year in AI and for SNNs + SELU!! See my overview and some trends here: Blog: bioinf-jku.github.io/SNNs/
3
1
13
875
📢 Another #NeurIPS, another diffusion circle! Join us to talk about diffusion models on Friday Dec 5 at 3:30PM in San Diego! Bayside terrace outside room 11 (upstairs) ☀️🚢🌊 Please help spread the word, tell your friends! No slides, no talks, we just sit down and chat 🗣️
7
34
6
214
64,446
Introducing our invited speakers at #ML4Molecules2025: Rocio Mercado ( rociomer.github.io ): Tenure-track professor at Chalmers University. Her work bridges machine learning and molecular discovery. Registration (free!): moleculediscovery.github.io/…
3
13
1,115
“In the judgement of the most competent living mathematicians, Fräulein Noether was the most significant creative mathematical genius thus far produced since the higher education of women began.” – Albert Einstein, 1935 (NYTimes) I’m thrilled to share that I’ll be joining emmi.ai, a company inspired by the legacy of Emmy Noether, for my upcoming internship. Over the next few months, I’ll have the opportunity to work with Sebastian Kaltenbach on my passion: Diffusion and Flow-based generative models, and their applications to physics. Excited for what lies ahead! While Noether devoted her life to uncovering the beauty of symmetries, our recent work explores a different path—approaching the problem without explicitly enforcing them. I’m proud that this work, done together with amazing collaborators @ArturToshev , Andreas Fürst, @gklambauer , @AndreasMayr11 , @jo_brandstetter , has been accepted to @NeurIPSConf 2025 in San Diego. arxiv.org/abs/2502.12128
3
159
Celebrating 4,000 citations! Thanks everyone who successfully used self-normalizing networks!!!
3
1
83
5,453
Nice, short post illustrating how simple text (discrete) diffusion can be. Diffusion (i.e. parallel, iterated denoising, top) is the pervasive generative paradigm in image/video, but autoregression (i.e. go left to right bottom) is the dominant paradigm in text. For audio I've seen a bit of both. A lot of diffusion papers look a bit dense but if you strip the mathematical formalism, you end up with simple baseline algorithms, e.g. something a lot closer to flow matching in continuous, or something like this in discrete. It's your vanilla transformer but with bi-directional attention, where you iteratively re-sample and re-mask all tokens in your "tokens canvas" based on a noise schedule until you get the final sample at the last step. (Bi-directional attention is a lot more powerful, and you get a lot stronger autoregressive language models if you train with it, unfortunately it makes training a lot more expensive because now you can't parallelize across sequence dim). So autoregression is doing an `.append(token)` to the tokens canvas while only attending backwards, while diffusion is refreshing the entire token canvas with a `.setitem(idx, token)` while attending bidirectionally. Human thought naively feels a bit more like autoregression but it's hard to say that there aren't more diffusion-like components in some latent space of thought. It feels quite possible that you can further interpolate between them, or generalize them further. And it's a component of the LLM stack that still feels a bit fungible. Now I must resist the urge to side quest into training nanochat with diffusion.
BERT is just a Single Text Diffusion Step! (1/n) When I first read about language diffusion models, I was surprised to find that their training objective was just a generalization of masked language modeling (MLM), something we’ve been doing since BERT from 2018. The first thought I had was, “can we finetune a BERT-like model to do text generation?”
265
518
68
5,156
872,513
PAPER/ABSTRACT DEADLINE ALREADY END OF THIS WEEK! ELLIS Machine Learning for Molecules workshop: moleculediscovery.github.io/… DON'T MISS THE DEADLINE: short papers or extended abstracts welcome!
1
1
10
739
🚀 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
40
13
231
85,123
It's happening again!!! ML4Molecules workshop 2025. within the #ELLIS Unconference, preceding #EurIPS. More infos: moleculediscovery.github.io/…
1
8
2
36
2,813
Florian retweeted
Paper by bytedance, improves upon Meanflow by removing the need for JVP calculation
6
22
1
213
14,783
Florian retweeted
if you're interested in building the future of creative tools with us, we're hiring! krea.ai/careers
4
2
1
23
6,484
🚀 Introducing XBai o4:a milestone in our 4th-generation open-source technology based on parallel test time scaling! In its medium mode, XBai o4 now fully outperforms OpenAI−o3−mini.📈 🔗Open-source weights: huggingface.co/MetaStoneTec/…✅ Github link: github.com/MetaStone-AI/XBai…
74
217
90
1,290
363,318
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.
10
69
8
320
39,715