Reusable pretrained wavefunctions will shorten the path from a Hamiltonian to a useful result, speeding the search for new materials and molecules.
The paper, weights, code and data are public: https://t.co/1B7dJiZghA
Hamilton-Zero starts from a shared checkpoint. We pretrained its 547M variational parameters across hundreds of thousands of Hamiltonians, fine-tuned it on systems up to 1,024 qubits and evaluated it zero-shot up to 8,100 qubits.
From @UChicago PhD in Computer Science to the @Forbes 30 Under 30 list
Elena Orlova studied under @WillettBecca. Now she's co-founded Simulacra AI with Aleksei Ustimenko and Fabio Falcioni, a company that cuts quantum simulation costs up to 50x, opening new doors for innovation
From @UChicago PhD in Computer Science to the @Forbes 30 Under 30 list
Elena Orlova studied under @WillettBecca. Now she's co-founded Simulacra AI with Aleksei Ustimenko and Fabio Falcioni, a company that cuts quantum simulation costs up to 50x, opening new doors for innovation
The biggest bottleneck in drug and materials discovery is physics simulation. That bottleneck was just solved.
We're excited to invest in @simulacraai, which has completed pre-training the world’s first Large Wavefunction Model. It changes everything👇
https://t.co/VV4n0DK2hQ
The biggest bottleneck in drug and materials discovery is physics simulation. That bottleneck was just solved.
We're excited to invest in @simulacraai, which has completed pre-training the world’s first Large Wavefunction Model. It changes everything👇
https://t.co/VV4n0DK2hQ
Heading to #NeurIPS2025 in San Diego!
Would be happy to chat about: datasets and evals for robotics, market-mechanism-aware AI, open-endedness, and scientific discovery.
Watch for the today’s announcement in the space of Foundational Large Wavefunction Models (!) for quantum chemistry.
We’ve been quiet, building in semi-stealth.
The benchmark is now public: https://t.co/TaeZVfz6xe
Simulacra AI generates quantum-accurate data 15–50× cheaper than Microsoft’s Orbformer and >2–3× cheaper than CCSD, with CCSD(T)-level accuracy.
Ab-initio at scale is no longer impossible.
If you’re in pharma and want access → [email protected]