3 papers
cs.LG2026
Learning Laplacian Eigenspace with Mass-Aware Neural Operators on Point Clouds
Zherui Yang, Tao Du, Ligang Liu
The eigendecomposition of the Laplace--Beltrami Operator (LBO) is fundamental to geometric analysis, yet computing its low-frequency eigenmodes remains a significant bottleneck due…
cs.LG2026
Simple yet Effective: Low-Rank Spatial Attention for Neural Operators
Zherui Yang, Haiyang Xin, Tao Du +1
Neural operators have emerged as data-driven surrogates for solving partial differential equations (PDEs), and their success hinges on efficiently modeling the long-range, global c…
cs.GR2025
An Adjoint Method for Differentiable Fluid Simulation on Flow Maps
Zhiqi Li, Jinjin He, Barnabás Börcsök +6
This paper presents a novel adjoint solver for differentiable fluid simulation based on bidirectional flow maps. Our key observation is that the forward fluid solver and its corres…