SP2RINT: Spatially-Decoupled Physics-Inspired Progressive Inverse Optimization for Scalable, PDE-Constrained Meta-Optical Neural Network Training

Ähnliche Einträge

• PIC2O-Sim: A Physics-Inspired Causality-Aware Dynamic Convolutional Neural Operator for Ultra-Fast Photonic Device FDTD Simulation
  von: Ma, Pingchuan, et al.
  Veröffentlicht: (2024)
• BOSON$^{-1}$: Understanding and Enabling Physically-Robust Photonic Inverse Design with Adaptive Variation-Aware Subspace Optimization
  von: Ma, Pingchuan, et al.
  Veröffentlicht: (2024)
• MAPS: Multi-Fidelity AI-Augmented Photonic Simulation and Inverse Design Infrastructure
  von: Ma, Pingchuan, et al.
  Veröffentlicht: (2025)
• SKYLIGHT: A Scalable Hundred-Channel 3D Photonic In-Memory Tensor Core Architecture for Real-time AI Inference
  von: Zhang, Meng, et al.
  Veröffentlicht: (2026)
• Toward Large-Scale Photonics-Empowered AI Systems: From Physical Design Automation to System-Algorithm Co-Exploration
  von: Yin, Ziang, et al.
  Veröffentlicht: (2025)