Claus (@ClausHofm) header
Claus (@ClausHofm) profile picture

PhD Candidate at the Institute for Machine Learning, Johannes Kepler University Linz. Curious about everything ML

Wien, Österreich
Joined February 2012
Photo by Claus (@ClausHofm)Photo by Claus (@ClausHofm)Photo by Claus (@ClausHofm)Photo by Claus (@ClausHofm)Photo by Claus (@ClausHofm)Photo by Claus (@ClausHofm)
🎉 Excited to share that our paper, AP-OOD, has been accepted at @iclr_conf! We introduce Attention Pooling for Out-of-Distribution Detection: AP-OOD detects OOD inputs in the latent token space of Transformer models, drastically improving results on natural language tasks.📈
2
3
21
1,447
xLSTM Distillation: arxiv.org/abs/2603.15590 Near-lossless distillation of quadratic Transformer LLMs into linear xLSTM architectures enables cost- and energy-efficient alternatives without sacrificing performance. xLSTM variants of instruction-tuned Llama, Qwen, & Olmo models.
5
57
8
307
25,010
📈Empirical results demonstrate that increasing the number of trainable weights in attention pooling consistently enhances OOD detection. This suggests that further scaling may yield additional performance gains.
1
221
🧪🧠 Do LLMs actually understand molecular structure? 📄 Paper: arxiv.org/pdf/2601.15279 🏆 Live leaderboard: huggingface.co/spaces/ml-jku… Introducing MolecularIQ — a benchmark designed to test real molecular understanding (not memorization).
3
4
5
187
# 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
Ever experienced instabilities when using the popular LV (Log Variance) loss for training Diffusion Bridge Samplers?
1
6
3
18
10,692
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%. P: arxiv.org/abs/2511.14744 Leaderboard: huggingface.co/spaces/ml-jku…
2
11
4
24
6,827
🚀 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
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
We release AB-UPT, a novel method to scale neural surrogates to CFD meshes beyond 100 million of mesh cells. AB-UPT is extensively tested on the largest publicly available datasets. 📄 arxiv.org/abs/2502.09692 🤗 huggingface.co/EmmiAI/AB-UPT 💻 github.com/Emmi-AI/AB-UPT
1
16
1
66
4,089
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
2
134
15,164
We’re excited to introduce TiRex — a pre-trained time series forecasting model based on an xLSTM architecture.
5
22
6
69
14,925
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
Need to predict bioactivity 🧪 but only have limited data ❌? Try our interactive app for prompting MHNfs — a state-of-the-art model for few-shot molecule–property prediction. No coding or training needed. 🚀 📄 Paper: pubs.acs.org/doi/10.1021/acs… 🖥️ App: huggingface.co/spaces/ml-jku…
12
1
16
1,353
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
21
1,773