A weighted FOSLS formulation for deep neural networks solves transmission problems robustly, with proofs that the loss aligns with the energy norm independently of material contrast and shows passive variance reduction.
A sample implementation for parallelizing divide-and-conquer algorithms on the GPU
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5representative citing papers
FusionRCG uses liveness-aware graph orchestration, Cartesian-to-spherical fusion, and multi-tier kernels to cut intermediate data by up to 7.7x and deliver 3.09x SCF speedup on A100 GPUs.
A stable and convergent finite element scheme is developed for the variable-order time-fractional incompressible MHD equations, with experiments showing the impact of variable orders on energy and enstrophy.
A genetic algorithm evolves CLIP token vectors to optimize aesthetic quality and prompt alignment in diffusion models, outperforming Promptist and random search by up to 23.93% on a combined fitness score.
Rotation of conducting and dielectric spheres in a uniform electrostatic field creates a braking torque from the tilted induced dipole, with integrable equations of motion solved explicitly in examples.
citing papers explorer
-
Robust Deep FOSLS for Transmission Problems
A weighted FOSLS formulation for deep neural networks solves transmission problems robustly, with proofs that the loss aligns with the energy norm independently of material contrast and shows passive variance reduction.
-
FusionRCG: Orchestrating Recursive Computation Graphs across GPU Memory Hierarchies
FusionRCG uses liveness-aware graph orchestration, Cartesian-to-spherical fusion, and multi-tier kernels to cut intermediate data by up to 7.7x and deliver 3.09x SCF speedup on A100 GPUs.
-
Numerical Analysis of a Variable-Order Time-Fractional Incompressible Magnetohydrodynamics System
A stable and convergent finite element scheme is developed for the variable-order time-fractional incompressible MHD equations, with experiments showing the impact of variable orders on energy and enstrophy.
-
Evolutionary Token-Level Prompt Optimization for Diffusion Models
A genetic algorithm evolves CLIP token vectors to optimize aesthetic quality and prompt alignment in diffusion models, outperforming Promptist and random search by up to 23.93% on a combined fitness score.
-
Free rotation of conducting and dielectric spheres in a uniform electrostatic field
Rotation of conducting and dielectric spheres in a uniform electrostatic field creates a braking torque from the tilted induced dipole, with integrable equations of motion solved explicitly in examples.