4 citations · 4 across the 4 of their papers we have counts for
5 papers
Photonics-GCCE: group collaborative-competitive evolution multi-agent framework for universal and autonomous optical design
Weijie Xu, Ming Wang, Ruicheng Ma +20
Large language model (LLM)-empowered photonic agents connect natural-language intents to executable solvers, showing significant advantages over conventional optical design approac…
High-capacity computing with self-rectification nonlinear optical neural processor
Ruicheng Ma, Siyu Dong, Yuzhi Shi +14
Artificial intelligence (AI) and neural networks have driven groundbreaking innovations across numerous disciplines. Optical computing offers the promise of unprecedented speed and…
Multi-channel Optical Vision Model
Ali Momeni, Guillaume Noetinger, Tim Tuuva +1
Spatial multiplexing is one of the natural strengths of optics, yet in optical neural networks, it is often used mainly as parallel throughput. Here, we show that spatial multiplex…
Expressivity of Programmable-Metasurface-Based Physical Neural Networks: Encoding Non-Linearity, Structural Non-Linearity, and Depth
Cheima Hammami, Luc Le Magoarou, Christos Monochristou +4
Wave-based signal processing conventionally encodes input data into the input wavefront, making it challenging to implement non-linear operations. Programmable wave systems enable…
Training of Physical Neural Networks
Ali Momeni, Babak Rahmani, Benjamin Scellier +25
Physical neural networks (PNNs) are a class of neural-like networks that leverage the properties of physical systems to perform computation. While PNNs are so far a niche research…