AI for Biological Discovery Methods Suite Released
MihaelaVDS · x · 2026-07-16
The van der Schaar Lab released its AI for Biological Discovery portfolio page, consolidating multiple methodological lines from the lab.
Core areas covered:
- Hypothesis discovery
- Interpretable rules
- Cell trajectory modeling
- Simulators
- Causal worlds
- Defensible prediction
The author emphasizes they have long focused on 'AI for real-world complexity' rather than just clean benchmarks; now applying this approach to biology research, welcoming contact on important biological/medical problems, datasets, or collaboration.
More from Research
- PyTorch practitioners are being urged to treat profiling as a basic skill — RisingSayak · 2026-07-21
- Two-hour workshop covers open models, benchmark cheating, reward hacking and quantization — danielhanchen · 2026-07-21
- Tau Ceti launches as an AI-formalized mathematics library for Lean — wellecks · 2026-07-21
- Researchers release 44B synthetic tokens for higher-quality pretraining data — vanstriendaniel · 2026-07-21
- ReViV reconstructs egocentric 4D viewer-and-scene dynamics from one monocular video — ethz-vlg · 2026-07-21
- A hand-worked batch norm example shows exactly what gets normalized and why — ProfTomYeh · 2026-07-21