3 papers
cs.NE2026
Provably Sub-Linear Two-Timescale NeuroEvolution with Online Plasticity
Shishen Lin, Yixin Chen
NeuroEvolution of Augmenting Topologies (NEAT) is a widely used neuroevolution algorithm for learning neural network architectures and weights for control tasks. However, standard…
cs.LG2026
Factorized Neural Implicit DMD for Parametric Dynamics
Siyuan Chen, Zhecheng Wang, Yixin Chen +4
A data-driven, model-free approach to modeling the temporal evolution of physical systems mitigates the need for explicit knowledge of the governing equations. Even when physical p…
cs.GR2025
Fast Subspace Fluid Simulation with a Temporally-Aware Basis
Siyuan Chen, Yixin Chen, Jonathan Panuelos +4
We present a novel reduced-order fluid simulation technique leveraging Dynamic Mode Decomposition (DMD) to achieve fast, memory-efficient, and user-controllable subspace simulation…