ByteCRN combines reaction enumeration with a unified generative rectified flow model for transition state generation and validation to achieve 10-100x acceleration and prune 70-90% of reactions in CRN exploration.
Enhancing gpu-acceleration in the python-based simulations of chemistry framework
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
physics.chem-ph 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Implements TDDFT-ris with density fitting and approximate Z-vector for fast excited-state gradients and nonadiabatic couplings in FSSH dynamics, claiming negligible errors and high efficiency for medium-sized systems.
citing papers explorer
-
A Unified Generative Framework for Scalable Chemical Reaction Network Exploration
ByteCRN combines reaction enumeration with a unified generative rectified flow model for transition state generation and validation to achieve 10-100x acceleration and prune 70-90% of reactions in CRN exploration.
-
TDDFT Gradients and Nonadiabatic Couplings with Minimal Auxiliary Basis Set Approximation for Fewest-Switches Surface Hopping Dynamics
Implements TDDFT-ris with density fitting and approximate Z-vector for fast excited-state gradients and nonadiabatic couplings in FSSH dynamics, claiming negligible errors and high efficiency for medium-sized systems.