AI for Scientific Discovery
Curated tools, papers, and opportunities. No hype—just what actually works.
Latest Updates
View all →58 papers from arXiv & bioRxiv · Updated 5/14/2026
CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks
arXiv:2605.12580v1 Announce Type: new Abstract: Randomized neural networks (RdNNs) enable efficient, backpropagation-free training by freezing randomly initialized input-to-hidden weights, which pe...
paperOceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocea...
arXiv:2605.12639v1 Announce Type: new Abstract: Extreme ocean phenomena are challenging not only to predict but to diagnose, as accurate forecasts alone do not reveal the underlying physical driver...
paperMulti-Rollout On-Policy Distillation via Peer Successes and Failures
arXiv:2605.12652v1 Announce Type: new Abstract: Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited g...
paperAlphaFold3: Accurate structure prediction of biomolecular interactions
DeepMind releases updated model handling proteins, DNA, RNA, ligands, and modifications.
toolChai-1: Open foundation model for molecular structure prediction
Multi-modal foundation model achieving state-of-the-art on drug-target interaction benchmarks.
newsRecursion acquires Exscientia for $688M in AI drug discovery consolidation
Major merger signals maturation of AI-native drug discovery platforms.
Categories
Research Papers
Curated papers from arXiv, bioRxiv, and journals with reproducible code and real-world impact.
ToolsModels & Tools
Open-source and commercial tools for drug discovery, protein design, and scientific computing.
JobsOpportunities
ML research roles at biotech companies, pharma, and academic labs.