Deep-QMC wavefunction foundation model in Nature Communications nails chemical bond breaking
FrankNoeBerlin · x · 2026-09-21
Frank Noé's group (Microsoft Research and collaborators) published an ab initio wavefunction foundation model in Nature Communications, based on deep Quantum Monte Carlo, that accurately describes chemical bond breaking — a long-standing challenge due to multireference electronic structure.
Conventional multireference methods are computationally costly and pay full price anew for each system, ignoring shared electronic-structure patterns across molecules; deep neural networks with QMC can exploit these commonalities. The open-access paper demonstrates accurate bond-breaking descriptions.
More from Research
- CVPR 2025 organizer: 90%+ of first authors had one submission, so authorship caps won't cut volume — CSProfKGD · 2026-09-22
- Toby Ord on swarm scaling: 10,000-agent run cost ~$20M, solved Navier-Stokes in 88 hours — tobyordoxford · 2026-09-22
- Toby Ord: Agent Swarm Estimates Put Intelligence Explosion Parameter λ at 0.5-0.6 — tobyordoxford · 2026-09-22
- Insilico Medicine signs co-development deal worth up to tens of millions with a frontier model lab — AllThingsApx · 2026-09-22
- Agent swarm data suggests intelligence explosion parameter λ around 0.5-0.6, below threshold — tobyordoxford · 2026-09-22
- Komlós Conjecture reportedly solved with a ~1-page proof, sparking debate — gautamcgoel · 2026-09-22