neural architectures
Neural architectures are the specific designs and structures of neural networks, including aspect like layers, activation functions, and connectivity patterns, which dictate their ability to learn from data and perform various tasks.
- AutoHood3D: A Multi‑Modal Benchmark for Automotive Hood Design and Fluid–Structure Interaction
- DeltaPhi: Physical States Residual Learning for Neural Operators in Data-Limited PDE Solving
- Infinite Neural Operators: Gaussian processes on functions
- Nested Learning: The Illusion of Deep Learning Architectures
- Neural Emulator Superiority: When Machine Learning for PDEs Surpasses its Training Data
- The Logical Expressiveness of Temporal GNNs via Two-Dimensional Product Logics
- Understanding and Enhancing Mask-Based Pretraining towards Universal Representations