Tag
A paper showing an LLM agent rewriting the Sella molecular geometry optimizer to cut force-evaluation counts, producing AutoSella, a family of optimizers that reduces r2SCAN-3c DFT force calls to 40.2–77.2% of Sella's while matching energy reduction on held-out molecules.
A novel AI model using a Fourier neural operator variant enables density functional theory to scale nearly linearly with system size, allowing efficient simulations of large quantum systems like a magnesium dislocation with 80k electrons on a single GPU.
Quantinuum, NVIDIA, and Pfizer have developed ADAPT-GQE, a generative quantum AI framework using transformer models to efficiently generate quantum chemistry circuits for molecular simulation and drug discovery.
OrbitAll is a molecular foundation model that uses physics-grounded orbital features and SE(3)-equivariant GNNs to predict molecular properties, outperforming larger models like UMA with 35x less training data and 50x smaller model size.
Quantinuum and SoftBank Corp. published a joint white paper mapping quantum computing use cases in quantum chemistry and graph analytics to Quantinuum's hardware roadmap, providing a framework for assessing when practical industrial applications become feasible.
Brown University chemists provide direct spectroscopic evidence that Einstein's theory of relativity blurs the distinction between sigma and pi bonds in heavy elements like bismuth, challenging textbook explanations.
This ICML 2026 paper introduces Derivative Informed XC-Loss (DI-Loss), a training approach for machine-learned exchange-correlation functionals that incorporates first and second derivative supervision on the Grassmannian of density matrices. Across four architectures, DI-Loss reduces total-energy MAE by 66% compared to energy and density supervision alone, and improves excited-state predictions in TDDFT calculations.
This paper introduces an adaptive on-the-fly multifidelity machine learning algorithm for quantum chemistry that autonomously determines training data composition across fidelities, reducing data generation costs by up to 30x compared to single-fidelity methods and up to 5x compared to standard multifidelity methods.
This paper introduces the Generative Quantum-inspired Kolmogorov-Arnold Eigensolver (GQKAE), a parameter-efficient architecture that replaces traditional neural components with Kolmogorov-Arnold modules to significantly reduce memory usage and improve convergence in quantum chemistry simulations.