An autonomous photonic device design agent, inspired by Andrej Karpathy's autoresearch. Instead of a human manually tuning device geometry and running simulations, an LLM agent (e.g. Claude Code) ...
u_{t+1} = P(u_t, u_{t-1}) + Δt² · F_θ(u_t) └── zero-param, differentiable └── lightweight perturbation wave propagation operator network (~3K params) crn/ ├── run.py # CLI entry point for all ...
FDTD simulations of a nanowire (NW) emitter-receiver pair calculating the fraction of the power of emitted light that is absorbed by the receiver (abs). (a) abs (λ) for devices realized on different ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results