Günter Klambauer

YouTube video by AI Podcast Series. Byte Goose AI. From HRM to RRM: Recurrent Reasoning Models. Is the SE-RRM the Ultimate Sudoku Challenger?

youtu.be/0qn2z9mD4Tc?...

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
C: github.com/ml-jku/SE-RRM

Hype um KI-Agent | DO | 05 02 2026 | 17:55 Was steckt hinter OpenClaw und Moltbook?

Mit #OpenClaw organisieren Nutzende ihr Leben. Der KI-Bot braucht dafür allerdings umfassenden Zugriff auf persönliche Daten. Und was hat es mit #Moltbook auf sich, wo sich diese Bots angeblich miteinander unterhalten? @gklambauer.bsky.social, Professor für KI an der JKU Linz, ordnet den Hype ein.

### NEW ENTRY IN THE AI IN DRUG DISCOVERY LEADERBOARD ###

CheMeleon takes the lead as the **best pre-trained model** and gets the Bronze medal (rank 3) overall.

It's an MPNN pre-trained to predict chemical descriptors.

P: arxiv.org/abs/2506.15792
C: github.com/JacksonBurns...

# 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

A NEW ENTRY TO THE TOX21 LEADERBOARD:

GROVER from TENCENT AI LAB obtains rank 5 on the Tox21 leaderboard. Best pre-trained model and clearly outperforms CHEMPROP.

Original implementation: github.com/tencent-aila...

Tox21 leaderboard on Hugging Face: huggingface.co/spaces/ml-jk...

xLSTM for Real-Time DNS Tunnel Detection: arxiv.org/abs/2512.09565

DNS-HyXNet = xLSTM for DNS tunnels.

DNS-HyXNet has 99.99% accuracy, with F1-scores exceeding 99.96%, and per-sample detection latency of just 0.041 ms, confirming its scalability and real-time readiness. wow!

EurIPS wird zur Bühne für europäische KI-Talente In Kopenhagen fand erstmals die EurIPS-Konferenz statt. Sie ist keine Gegenveranstaltung zur berühmten amerikanischen NeurIPS, sondern eine Bühne für erstklassige europäische KI-Forschung. Jetzt sind ...

Sepp Hochreiter, Head of LIT AI Lab, comments on the EurIPS conference in this FAZ guest article:
He highlights Europe’s growing visibility in AI research and the role of ELLIS in strengthening the community. 🌍
www.faz.net/pro/digitalw...

Measuring AI Progress in Drug Discovery: A Reproducible Leaderboard for the Tox21 Challenge Deep learning's rise since the early 2010s has transformed fields like computer vision and natural language processing and strongly influenced biomedical research. For drug discovery specifically, a k...

Drug discovery benchmarks reveal a surprising result: the original 2017 SELU networks still dominate toxicity prediction (Tox21).
P: arxiv.org/abs/2511.14744

GyralNet Subnetwork Partitioning via Differentiable Spectral Modularity Optimization Understanding the structural and functional organization of the human brain requires a detailed examination of cortical folding patterns, among which the three-hinge gyrus (3HG) has been identified as...

GCN variants (e.g., GyralNet) increasingly replace ReLU with SELU for better convergence and robustness in noisy or shallow graph settings.
P: arxiv.org/abs/2503.19823

Pearl: Automatic Code Optimization Using Deep Reinforcement Learning Compilers are crucial in optimizing programs and accelerating their execution. However, optimizing programs automatically using compilers is not trivial. Recent work has attempted to use reinforcement...

SELU made a comeback in RL: PPO-based systems like Pearl report smoother, more stable actor–critic updates when batchnorm is avoided.
P: arxiv.org/abs/2506.01880

The SELU-transformer resurged in NLP/tabular domains -- TabTranSELU even kicks out SwiGLU entirely.
P: doi.org/10.54254/275...

FlowState: Sampling Rate Invariant Time Series Forecasting Foundation models (FMs) have transformed natural language processing, but their success has not yet translated to time series forecasting. Existing time series foundation models (TSFMs), often based o...

Flowstate continued the trend: SELU activations bring stability in large-scale time-series models.
P: arxiv.org/abs/2508.05287

Time-series foundation models (FIM/FIM-ℓ, Flowstate) all quietly adopt SELU, and TiRex topped the GIFT Eval leaderboard this year.
P: openreview.net/forum?id=NPS...

Improving and generalizing flow-based generative models with minibatch optimal transport Continuous normalizing flows (CNFs) are an attractive generative modeling technique, but they have been held back by limitations in their simulation-based maximum likelihood training. We introduce the...

Tiny SELU MLPs (2–3 layers, width 64) became the standard in Conditional Flow Matching, thanks to smoother derivative behavior than ReLU.
P: arxiv.org/abs/2302.00482

Transformers without Normalization Normalization layers are ubiquitous in modern neural networks and have long been considered essential. This work demonstrates that Transformers without normalization can achieve the same or better per...

Normalization-Free Transformers rediscover controlled signal propagation — a core idea behind SNNs.
P: arxiv.org/abs/2503.10622

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:
bioinf-jku.github.io/SNNs/

Land fördert die Kepler-Uni in den kommenden drei Jahren mit 22,5 Millionen Euro LINZ. Dritte Fördervereinbarung sieht Schwerpunkte bei Künstlicher Intelligenz, Quantenwissenschaft und Internationalisierung vor.

Great news for AI research at JKU!
Upper Austria invests €22.5M to strengthen AI & quantum science, supporting the ELLIS Unit Linz and the LIT AI Lab.
This commitment boosts new projects, talent, collaborations & innovation made in Austria 🇦🇹
www.nachrichten.at/politik/land...

Thanks for more than 1000 visits to the leaderboard in the last 2 days!

YOU THINK YOU HAVE A BETTER MODEL?? GREAT! Training models on the Tox21 Challenge dataset can be done on a laptop-GPU.

Submit your model to the leaderboard! Click SUBMIT here: huggingface.co/spaces/ml-jk...

AI is hitting a wall in drug discovery!

Here is the wall you were all looking for...

huggingface.co/spaces/ml-jk...

Yes, ECFP plus some other descriptors.. should be in the model-cards and the paper ..

You have access to the model predictions via API call.

Just type:

curl -X POST ml-jku-tox21-gin-classifier.hf.space/predict -H "Content-Type: application/json" -d '{"smiles": ["CCO", "c1ccccc1"]}'

in your shell.

Measuring AI Progress in Drug Discovery - A NEW LEADERBOARD IN TOWN

2015-2025: turns out that there's hardly any improvement. AI bubble?

GPT is at 70% for this task, whereas the best methods get close to 85%.

Leaderboard: huggingface.co/spaces/ml-jk...
P: arxiv.org/abs/2511.14744

List of accepted contributions now online: moleculediscovery.github.io/workshop2025/

Roughly 50% of the tickets already gone...

Indeed.. :)

How many errors do you find in the chemical structure above?

Hab mir einen Mahrer Tracker gebaut. Spannend zu sehen, wie schnell Print-Medien auf ihren Online-Portalen auf Dinge wie ein ZIB 2 Interview reagieren und wie sich die Inhalte dabei unterscheiden.

ELLIS Machine Learning for Molecules Workshop 2025 - Virtual participation Workshop on generative Models, LLMs, and the Future of Molecular AI. For details, see: https://moleculediscovery.github.io/workshop2025/

ELLIS ML4Molecules Workshop 2025: Registration for virtual participation now open!!!

Only 500 tickets available which usually are gone fast!!

Register now: www.eventbrite.com/e/ellis-mach...

Speaker 4 at ELLIS ML4Molecules 2025: Nadine Schneider

Early works on ML methods for chemical reactions. Introduced the FS-Mol datasets for few-shot learning for molecules. Director of the ELLIS ML for Molecules Discovery program.

Join the workshop: moleculediscovery.github.io/workshop2025/