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
- Autonomous agent edits just 1,024 weights to lift Qwen3.5 0.8B from 7.4% to 37.4% on MATH-500 — VictorSanh · 2026-11-12
- Gait dataset labeled by encounter, spanning pre-op to 3 months post-TKA — zawthet · 2026-11-12
- Walking alignment measured 2.5-3.1° more neutral than X-ray, iPad gait study finds — zawthet · 2026-11-12
- MIT's Tegmark coins 'formal-washing': Signal protocol proof is far from complete — tegmark · 2026-11-12
- Signal formal verification hits 80%, Tegmark says Wired overstated completion — tegmark · 2026-11-12
- Category-theoretic framework asks: when does a physical system actually compute? — neurovium · 2026-11-12