FRAMES training with minimal temporal information from MD trajectory pairs improves energy and force prediction accuracy over Equiformer on MD17 and ISO17 benchmarks.
Equivariant graph neural operator for modeling 3d dynamics.arXiv preprint arXiv:2401.11037
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
AeTHERON achieves mean extrapolation MAE of 0.168 while qualitatively capturing vortex topology on unseen timesteps of flapping flexible caudal fin FSI simulations.
Neural operators supply warm-start guesses that cut iteration counts and runtime by up to 90% in Krylov solvers for PDEs while retaining the original methods' convergence guarantees.
PAINET proposes an SE(3)-equivariant transformer with physics-inspired attention from energy minimization for 3D dynamics modeling, reporting 4.7-41.5% error reductions on human motion, molecular, and protein benchmarks.
GRWM uses temporal contrastive learning to geometrically regularize latent spaces in world models for high-fidelity cloning of deterministic 3D worlds.
citing papers explorer
-
Improving Molecular Force Fields with Minimal Temporal Information
FRAMES training with minimal temporal information from MD trajectory pairs improves energy and force prediction accuracy over Equiformer on MD17 and ISO17 benchmarks.
-
AeTHERON: Autoregressive Topology-aware Heterogeneous Graph Operator Network for Fluid-Structure Interaction
AeTHERON achieves mean extrapolation MAE of 0.168 while qualitatively capturing vortex topology on unseen timesteps of flapping flexible caudal fin FSI simulations.
-
NOWS: Neural Operator Warm Starts for Accelerating Iterative Solvers
Neural operators supply warm-start guesses that cut iteration counts and runtime by up to 90% in Krylov solvers for PDEs while retaining the original methods' convergence guarantees.
-
PAINET: A Principled Efficient Transformer for 3D Dynamics Modeling
PAINET proposes an SE(3)-equivariant transformer with physics-inspired attention from energy minimization for 3D dynamics modeling, reporting 4.7-41.5% error reductions on human motion, molecular, and protein benchmarks.
-
Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models
GRWM uses temporal contrastive learning to geometrically regularize latent spaces in world models for high-fidelity cloning of deterministic 3D worlds.