Philipp Seidl

Yesterday, I successfully defended my PhD dissertation on 'Multimodal Contrastive Learning for Drug Discovery' 🎓. I'm proud of our work, which demonstrates how to exploit multiple modalities in drug discovery using contrastive learning and modern Hopfield networks.

AI for biomedical imaging breaks when you change the lab, device, or batch. New paper fixes this using the control samples already in your experiment. The forgotten controls (and meta-learning) were the answer all along. P: arxiv.org/abs/2604.20824

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

🎉 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.📈

🏆 MolecularIQ is live — and open to the community 👉 Check how current LLMs perform on real molecular structure reasoning 👉 Submit your own chemistry LLM and get evaluated under a standardized protocol 🔗 Leaderboard & submissions: huggingface.co/spaces/ml-jku/…

ELLIS ML4Molecules Workshop running at the Ellis Unconference at #EurIPS, Copenhagen.

Interested in how we can use ideas from Flash Attention for more efficient linear RNN kernels? I am heading to NeurIPS in San Diego to present our work on Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels.

🚀 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

A devastating blow for GNNs/MPNNs in chemistry... P: arxiv.org/abs/2508.06199

"All models, except CLAMP, are either worse than or practically equivalent to the baseline ECFP fingerprint on molecular property prediction tasks." from Benchmarking Pretrained Molecular Embedding Models arxiv.org/pdf/2508.06199 - honored =)

reasoning traces have been generated by showing the ground-truth reaction, and letting a RLLM reason through it

Specifically trained reasoning LLM on retrosynthesis data (trained on USPTO-full wo 50k-test, though)

from arxiv.org/pdf/2507.17448

nice overview - from arxiv.org/pdf/2503.16419

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.

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

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-SLi… 📝Blog: ml-jku.github.io/LaM-SLidE/ 1/n

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/ac… 🖥️ App: huggingface.co/spaces/ml-jku/…

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

A User-Tunable Machine Learning Framework for Step-Wise Synthesis Planning Chemical reactions & synthesis with NEURO-SYMBOLIC AI: - (modern) Hopfield networks used - Reaction templates (symbolic rules) 🧪🧠 P: arxiv.org/abs/2504.02191

Yesterday, we shared the details on our xLSTM 7B architecture. Now, let's go one level deeper🧑‍🔧 We introduce ⚡️Tiled Flash Linear Attention (TFLA), ⚡️ A new kernel algorithm for the mLSTM and other Linear Attention variants with Gating. We find TFLA is really fast! 🧵(1/11)