Digital microfluidics (DMF) is a versatile technique for parallel and field-programmable control of individual droplets. Given the high level of variability in droplet manipulation, it is essential to establish self-adaptive and intelligent control methods for DMF systems that are informed by the transient state of droplets and their interactions. However, most related studies focus on droplet localization and shape recognition. In this study, we develop the AI-assisted DMF framework μDropAI for multistate droplet control on the basis of droplet morphology. The semantic segmentation model is integrated into our custom-designed DMF system to recognize the droplet states and their interactions for feedback control with a state machine. The proposed model has strong flexibility and can recognize droplets of different colors and shapes with an error rate of less than 0.63%; it enables control of droplets without user intervention. The coefficient of variation (CV) of the volumes of split droplets can be limited to 2.74%, which is lower than the CV of traditional dispensed droplets, contributing to an improvement in the precision of volume control for droplet splitting. The proposed system inspires the development of semantic-driven DMF systems that can interface with multimodal large language models (MLLMs) for fully automatic control.

To enable electrochemistry-based sensors to be applied under size and cost sensitive conditions, we developed a thumb-size electrochemistry instrument system (MiniEC) with integrated components including an electrochemical sensing interface, signal transduction, amplification, filtering, processing and transmission with a cost of around only $15. We showed its potential application for electrochemical studies and on-site environmental monitoring in a wide range of environments such as laboratory, household, countryside, industry or wild settings. By using the MiniEC with screen printed electrodes, the LOD (limit of detection) for Cd²⁺ and Pb²⁺ is as low as 1 μg L⁻¹ and 0.5 μg L⁻¹, respectively.

The human visual nervous system excels at recognizing and processing external stimuli, essential for various physiological functions. Biomimetic visual systems leverage biological synapse properties to improve memory encoding and perception. Optoelectronic devices mimicking these synapses can enhance wearable electronics, with layered heterojunction materials being ideal materials for optoelectronic synapses due to their tunable properties and biocompatibility. However, conventional synthesis methods are complex and environmentally harmful, leading to issues such as poor stability and low charge transfer efficiency. Therefore, it is imperative to develop a more efficient, convenient, and eco‐friendly method for preparing layered heterojunction materials. Here, a one‐step ultrasonic method is employed to mix fullerene (C60) with graphene oxide (GO), yielding a homogeneous layered heterojunction composite film via self‐assembly. The biomimetic optoelectronic synapse based on this film achieves 97.3% accuracy in dynamic visual recognition tasks and exhibits capabilities such as synaptic plasticity. Experiments utilizing X‐ray photoelectron spectroscopy (XPS), X‐ray diffraction spectroscopy (XRD), Fourier–transform infrared spectroscopy (FTIR), ultraviolet‐visible spectroscopy (UV‐vis), scanning electron microscopy (SEM), and transmission electron microscopy (TEM) confirms stable π‐π interactions between GO and C60, facilitating electron transfer and prolonging carrier recombination times. The novel approach leveraging high‐density π electron materials advances artificial intelligence and neuromorphic systems.