Günter Klambauer
@gklambauer.bsky.social
Deep Learning researcher | professor for Artificial Intelligence in Life Sciences | inventor of self-normalizing neural networks | ELLIS program Director
AI is hitting a wall in drug discovery!
Here is the wall you were all looking for...
huggingface.co/spaces/ml-jk...
Here is the wall you were all looking for...
huggingface.co/spaces/ml-jk...
November 19, 2025 at 12:38 PM
AI is hitting a wall in drug discovery!
Here is the wall you were all looking for...
huggingface.co/spaces/ml-jk...
Here is the wall you were all looking for...
huggingface.co/spaces/ml-jk...
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.
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.
November 19, 2025 at 6:52 AM
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.
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
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
November 19, 2025 at 6:52 AM
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
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/
November 17, 2025 at 3:50 PM
List of accepted contributions now online: moleculediscovery.github.io/workshop2025/
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/
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/
November 13, 2025 at 6:46 AM
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/
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/
Invited speaker 3 at #ML4Molecules2025: Daniel Probst ( @skepteis.bsky.social ).
He is known for his works on exploring chemical spaces, fingerprints, language models,... and some unconventional ideas like learning on gzip compressed data.
Join: moleculediscovery.github.io/workshop2025/
He is known for his works on exploring chemical spaces, fingerprints, language models,... and some unconventional ideas like learning on gzip compressed data.
Join: moleculediscovery.github.io/workshop2025/
November 12, 2025 at 7:46 AM
Invited speaker 3 at #ML4Molecules2025: Daniel Probst ( @skepteis.bsky.social ).
He is known for his works on exploring chemical spaces, fingerprints, language models,... and some unconventional ideas like learning on gzip compressed data.
Join: moleculediscovery.github.io/workshop2025/
He is known for his works on exploring chemical spaces, fingerprints, language models,... and some unconventional ideas like learning on gzip compressed data.
Join: moleculediscovery.github.io/workshop2025/
@marwinsegler.bsky.social will talk about "Deep Learning for Molecules: The First Decade" at #ML4Molecules2025
In pioneering work, he introduced a "small LLM" for generating SMILES strings back in 2016/17. Chemical synthesis prediction with MCTS; ...
Join: moleculediscovery.github.io/workshop2025/
In pioneering work, he introduced a "small LLM" for generating SMILES strings back in 2016/17. Chemical synthesis prediction with MCTS; ...
Join: moleculediscovery.github.io/workshop2025/
November 10, 2025 at 6:32 AM
@marwinsegler.bsky.social will talk about "Deep Learning for Molecules: The First Decade" at #ML4Molecules2025
In pioneering work, he introduced a "small LLM" for generating SMILES strings back in 2016/17. Chemical synthesis prediction with MCTS; ...
Join: moleculediscovery.github.io/workshop2025/
In pioneering work, he introduced a "small LLM" for generating SMILES strings back in 2016/17. Chemical synthesis prediction with MCTS; ...
Join: moleculediscovery.github.io/workshop2025/
Celebrating 4,000 citations!
Thanks to everyone who successfully used self-normalizing networks!!!
Thanks to everyone who successfully used self-normalizing networks!!!
October 21, 2025 at 10:50 AM
Celebrating 4,000 citations!
Thanks to everyone who successfully used self-normalizing networks!!!
Thanks to everyone who successfully used self-normalizing networks!!!
PAPER/ABSTRACT DEADLINE ALREADY END OF THIS WEEK!
ELLIS Machine Learning for Molecules workshop: moleculediscovery.github.io/workshop2025/
DON'T MISS THE DEADLINE: short papers or extended abstracts welcome!
ELLIS Machine Learning for Molecules workshop: moleculediscovery.github.io/workshop2025/
DON'T MISS THE DEADLINE: short papers or extended abstracts welcome!
October 7, 2025 at 8:48 AM
PAPER/ABSTRACT DEADLINE ALREADY END OF THIS WEEK!
ELLIS Machine Learning for Molecules workshop: moleculediscovery.github.io/workshop2025/
DON'T MISS THE DEADLINE: short papers or extended abstracts welcome!
ELLIS Machine Learning for Molecules workshop: moleculediscovery.github.io/workshop2025/
DON'T MISS THE DEADLINE: short papers or extended abstracts welcome!
ELLIS ML4Molecules workshop 2025
** Call for papers** is out: moleculediscovery.github.io/workshop2025/
** Call for papers** is out: moleculediscovery.github.io/workshop2025/
September 29, 2025 at 3:54 PM
ELLIS ML4Molecules workshop 2025
** Call for papers** is out: moleculediscovery.github.io/workshop2025/
** Call for papers** is out: moleculediscovery.github.io/workshop2025/
It's happening again!!!
ML4Molecules workshop 2025.
within the #ELLIS Unconference, preceding #EurIPS.
More infos: moleculediscovery.github.io/workshop2025/
ML4Molecules workshop 2025.
within the #ELLIS Unconference, preceding #EurIPS.
More infos: moleculediscovery.github.io/workshop2025/
September 23, 2025 at 6:12 AM
It's happening again!!!
ML4Molecules workshop 2025.
within the #ELLIS Unconference, preceding #EurIPS.
More infos: moleculediscovery.github.io/workshop2025/
ML4Molecules workshop 2025.
within the #ELLIS Unconference, preceding #EurIPS.
More infos: moleculediscovery.github.io/workshop2025/
Happy that IBM uses proper MLPs, i.e. self-normalizing networks, in their Flowstate model! ;)
P: arxiv.org/abs/2508.05287
P: arxiv.org/abs/2508.05287
September 17, 2025 at 9:20 AM
Happy that IBM uses proper MLPs, i.e. self-normalizing networks, in their Flowstate model! ;)
P: arxiv.org/abs/2508.05287
P: arxiv.org/abs/2508.05287
Machine Learning-Driven Optimization of Specific, Compact, and Efficient Base Editors via Single-Round Diversification
New base editors designed and optimized with ML! Almost all ML-designed ones active in the lab tests!!
P: www.biorxiv.org/content/10.1...
New base editors designed and optimized with ML! Almost all ML-designed ones active in the lab tests!!
P: www.biorxiv.org/content/10.1...
August 12, 2025 at 9:54 AM
Machine Learning-Driven Optimization of Specific, Compact, and Efficient Base Editors via Single-Round Diversification
New base editors designed and optimized with ML! Almost all ML-designed ones active in the lab tests!!
P: www.biorxiv.org/content/10.1...
New base editors designed and optimized with ML! Almost all ML-designed ones active in the lab tests!!
P: www.biorxiv.org/content/10.1...
Devastating blow for GNNs/MPNNs for chemistry and small molecules:
All of them are not statistically better than simple ECFP . Only our CLAMP model does the job ;)
P: arxiv.org/abs/2508.06199
All of them are not statistically better than simple ECFP . Only our CLAMP model does the job ;)
P: arxiv.org/abs/2508.06199
August 11, 2025 at 3:31 PM
Devastating blow for GNNs/MPNNs for chemistry and small molecules:
All of them are not statistically better than simple ECFP . Only our CLAMP model does the job ;)
P: arxiv.org/abs/2508.06199
All of them are not statistically better than simple ECFP . Only our CLAMP model does the job ;)
P: arxiv.org/abs/2508.06199
Just in: GPT-5 achieves AGI in chemical sciences!!1!!1!
Actually, NO! .... struggles with generating 2D graphs from SMILES.
Actually, NO! .... struggles with generating 2D graphs from SMILES.
August 11, 2025 at 5:37 AM
Just in: GPT-5 achieves AGI in chemical sciences!!1!!1!
Actually, NO! .... struggles with generating 2D graphs from SMILES.
Actually, NO! .... struggles with generating 2D graphs from SMILES.
Recommended read for the weekend: Sepp Hochreiter's book on AI!
Lots of fun anecdotes and easily accessible basics on AI!
www.beneventopublishing.com/ecowing/prod...
Lots of fun anecdotes and easily accessible basics on AI!
www.beneventopublishing.com/ecowing/prod...
May 30, 2025 at 12:28 PM
Recommended read for the weekend: Sepp Hochreiter's book on AI!
Lots of fun anecdotes and easily accessible basics on AI!
www.beneventopublishing.com/ecowing/prod...
Lots of fun anecdotes and easily accessible basics on AI!
www.beneventopublishing.com/ecowing/prod...
Latent Space Modeling of Spatial Dynamical Systems via
Linked Entities
LATENT DIFFUSION and GRAPH NEURAL NETWORKS finally combined!!
Best model for molecular dynamics of small molecules!!!
Paper: arxiv.org/abs/2502.121...
Blog: ml-jku.github.io/LaM-SLidE/
Linked Entities
LATENT DIFFUSION and GRAPH NEURAL NETWORKS finally combined!!
Best model for molecular dynamics of small molecules!!!
Paper: arxiv.org/abs/2502.121...
Blog: ml-jku.github.io/LaM-SLidE/
May 22, 2025 at 12:50 PM
Latent Space Modeling of Spatial Dynamical Systems via
Linked Entities
LATENT DIFFUSION and GRAPH NEURAL NETWORKS finally combined!!
Best model for molecular dynamics of small molecules!!!
Paper: arxiv.org/abs/2502.121...
Blog: ml-jku.github.io/LaM-SLidE/
Linked Entities
LATENT DIFFUSION and GRAPH NEURAL NETWORKS finally combined!!
Best model for molecular dynamics of small molecules!!!
Paper: arxiv.org/abs/2502.121...
Blog: ml-jku.github.io/LaM-SLidE/
Leveraging Partial SMILES Validation Scheme for Enhanced Drug Design in Reinforcement Learning Frameworks
Uncomplete SMILES strings already assessed during autoregressive generation. Decreases amount of incorrect molecules.
P: arxiv.org/abs/2505.00530
Uncomplete SMILES strings already assessed during autoregressive generation. Decreases amount of incorrect molecules.
P: arxiv.org/abs/2505.00530
May 5, 2025 at 6:16 AM
Leveraging Partial SMILES Validation Scheme for Enhanced Drug Design in Reinforcement Learning Frameworks
Uncomplete SMILES strings already assessed during autoregressive generation. Decreases amount of incorrect molecules.
P: arxiv.org/abs/2505.00530
Uncomplete SMILES strings already assessed during autoregressive generation. Decreases amount of incorrect molecules.
P: arxiv.org/abs/2505.00530
MHNfs: Prompting In-Context Bioactivity Predictions for Low-Data Drug Discovery
Few-shot models for molecules now easily accessible via web application. Predictions via prompting SMILES
P: pubs.acs.org/doi/10.1021/...
Few-shot models for molecules now easily accessible via web application. Predictions via prompting SMILES
P: pubs.acs.org/doi/10.1021/...
May 2, 2025 at 6:26 AM
MHNfs: Prompting In-Context Bioactivity Predictions for Low-Data Drug Discovery
Few-shot models for molecules now easily accessible via web application. Predictions via prompting SMILES
P: pubs.acs.org/doi/10.1021/...
Few-shot models for molecules now easily accessible via web application. Predictions via prompting SMILES
P: pubs.acs.org/doi/10.1021/...
Softpick: No Attention Sink, No Massive Activations with Rectified Softmax
Work claims that asing softpick instead of softmax in LLM training removes attention sinks and massive activations. Run with 0.37B parameter LLM similar to normal attention
P: arxiv.org/abs/2504.20966
Work claims that asing softpick instead of softmax in LLM training removes attention sinks and massive activations. Run with 0.37B parameter LLM similar to normal attention
P: arxiv.org/abs/2504.20966
April 30, 2025 at 5:11 AM
Softpick: No Attention Sink, No Massive Activations with Rectified Softmax
Work claims that asing softpick instead of softmax in LLM training removes attention sinks and massive activations. Run with 0.37B parameter LLM similar to normal attention
P: arxiv.org/abs/2504.20966
Work claims that asing softpick instead of softmax in LLM training removes attention sinks and massive activations. Run with 0.37B parameter LLM similar to normal attention
P: arxiv.org/abs/2504.20966
Unified Molecule Generation and Property Prediction
Transformer trained to jointly generate molecules and predict molecular properties. Task-tokens used for different properties. Encoder-decoder architecture.
P: arxiv.org/abs/2504.16559
Transformer trained to jointly generate molecules and predict molecular properties. Task-tokens used for different properties. Encoder-decoder architecture.
P: arxiv.org/abs/2504.16559
April 24, 2025 at 6:05 AM
Unified Molecule Generation and Property Prediction
Transformer trained to jointly generate molecules and predict molecular properties. Task-tokens used for different properties. Encoder-decoder architecture.
P: arxiv.org/abs/2504.16559
Transformer trained to jointly generate molecules and predict molecular properties. Task-tokens used for different properties. Encoder-decoder architecture.
P: arxiv.org/abs/2504.16559
Diverse and feasible retrosynthesis using GFlowNetsDiverse and feasible retrosynthesis using GFlowNets
Predicting/generating chemical reactions. Semi-template approach with GFlowNets as generative model. Lots of evaluations, e.g. multi-step retrosynthesis.
P: www.sciencedirect.com/science/arti...
Predicting/generating chemical reactions. Semi-template approach with GFlowNets as generative model. Lots of evaluations, e.g. multi-step retrosynthesis.
P: www.sciencedirect.com/science/arti...
April 23, 2025 at 6:06 AM
Diverse and feasible retrosynthesis using GFlowNetsDiverse and feasible retrosynthesis using GFlowNets
Predicting/generating chemical reactions. Semi-template approach with GFlowNets as generative model. Lots of evaluations, e.g. multi-step retrosynthesis.
P: www.sciencedirect.com/science/arti...
Predicting/generating chemical reactions. Semi-template approach with GFlowNets as generative model. Lots of evaluations, e.g. multi-step retrosynthesis.
P: www.sciencedirect.com/science/arti...
xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference
Meet the fastest 7B language model out there. Based on the mLSTM!
P: arxiv.org/abs/2503.13427
Meet the fastest 7B language model out there. Based on the mLSTM!
P: arxiv.org/abs/2503.13427
March 18, 2025 at 6:33 AM
xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference
Meet the fastest 7B language model out there. Based on the mLSTM!
P: arxiv.org/abs/2503.13427
Meet the fastest 7B language model out there. Based on the mLSTM!
P: arxiv.org/abs/2503.13427
The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems
A set of tasks/question for LLMs where they are pressured to lie (e.g. to "costumers"). Grok has highest tendency to lie; Claude 3.7 least..
P: arxiv.org/abs/2503.03750
A set of tasks/question for LLMs where they are pressured to lie (e.g. to "costumers"). Grok has highest tendency to lie; Claude 3.7 least..
P: arxiv.org/abs/2503.03750
March 6, 2025 at 8:06 AM
The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems
A set of tasks/question for LLMs where they are pressured to lie (e.g. to "costumers"). Grok has highest tendency to lie; Claude 3.7 least..
P: arxiv.org/abs/2503.03750
A set of tasks/question for LLMs where they are pressured to lie (e.g. to "costumers"). Grok has highest tendency to lie; Claude 3.7 least..
P: arxiv.org/abs/2503.03750