QERNEL: a Scalable Large Electron Model
📰 ArXiv cs.AI
Learn about QERNEL, a scalable large electron model that solves many-electron Hamiltonians using a foundational neural wavefunction
Action Steps
- Apply QERNEL to solve many-electron Hamiltonians using a neural wavefunction
- Use FiLM-based parameter conditioning to improve expressivity
- Implement mixture of experts and grouped-query attention to reduce computational cost
- Evaluate QERNEL's performance on various parameterized Hamiltonians
- Compare QERNEL's results with existing methods for solving many-electron systems
Who Needs to Know This
Researchers and engineers working on quantum mechanics and machine learning can benefit from QERNEL's ability to variationally solve families of parameterized many-electron Hamiltonians
Key Insight
💡 QERNEL combines FiLM-based parameter conditioning with scale-efficient architectural elements to improve expressivity at low computational cost
Share This
🚀 Introducing QERNEL, a scalable large electron model that solves many-electron Hamiltonians using a neural wavefunction 🤯
Key Takeaways
Learn about QERNEL, a scalable large electron model that solves many-electron Hamiltonians using a foundational neural wavefunction
Full Article
Title: QERNEL: a Scalable Large Electron Model
Abstract:
arXiv:2604.26018v1 Announce Type: cross Abstract: We introduce QERNEL, a foundational neural wavefunction that variationally solves families of parameterized many-electron Hamiltonians and captures their ground states throughout parameter space within a single model. QERNEL combines FiLM-based parameter conditioning with scale-efficient architectural elements -- mixture of experts and grouped-query attention, substantially improving expressivity at low computational cost. We apply QERNEL to inte
Abstract:
arXiv:2604.26018v1 Announce Type: cross Abstract: We introduce QERNEL, a foundational neural wavefunction that variationally solves families of parameterized many-electron Hamiltonians and captures their ground states throughout parameter space within a single model. QERNEL combines FiLM-based parameter conditioning with scale-efficient architectural elements -- mixture of experts and grouped-query attention, substantially improving expressivity at low computational cost. We apply QERNEL to inte
DeepCamp AI