Broadband All-Optical Memtransistor Based on Organic Cocrystals for Noise-Robust Motion Recognition

All-optical artificial synaptic devices offer promising potential for neuromorphic computing, yet their development is hindered by limited spectral tunability and poor plasticity linearity. Here, a broadband all-optical synaptic memtransistor based on organic charge transfer cocrystals (DTT-TCNQ) is reported, which enables fully light-driven and reversible modulation of synaptic weights across a wide wavelength range (395-808 nm). The device exhibits bidirectional excitatory and inhibitory photoresponses, and achieves highly linear long-term potentiation and depression (LTP/LTD) characteristics with ultralow nonlinearity (α_p = 0.00191, α_d = 0.00305) and asymmetry ratio (AR = 0.00114), attributed to a synergistic strategy combining frequency modulation and photoelectric coupling. When integrated into a convolutional neural long short-term memory network (CNN-LSTM) hybrid network, the device enables rapid convergence (98.77% accuracy in 6 training epochs) and robust recognition performance under spatiotemporal noise, outperforming conventional light-write/electric-erasing schemes. This work bridges material-level innovation and system-level functionality, offering a scalable approach toward energy-efficient, noise-resilient neuromorphic vision systems.