Glove-based human–machine interfaces (HMIs) offer a natural, intuitive way to capture finger motions for gesture recognition, virtual interaction, and robotic control. However, many existing systems suffer from complex fabrication, limited sensitivity, and reliance on external power. Here, we present a flexible, self-powered glove HMI based on a minimalist triboelectric nanogenerator (TENG) sensor composed of a conductive fabric electrode and textured Ecoflex layer. Surface micro-structuring via 3D-printed molds enhances triboelectric performance without added complexity, achieving a peak power density of 75.02 μW/cm² and stable operation over 13,000 cycles. The glove system enables real-time LED brightness control via finger-bending kinematics and supports intelligent recognition applications. A convolutional neural network (CNN) achieves 99.2% accuracy in user identification and 97.0% in object classification. By combining energy autonomy, mechanical simplicity, and machine learning capabilities, this work advances scalable, multi-functional HMIs for applications in assistive robotics, augmented reality (AR)/(virtual reality) VR environments, and secure interactive systems.

Prompt tuning visual-language models (VLMs) for specialized tasks often involves leveraging task-specific textual tokens, which can tailor the pre-existing, broad capabilities of a VLM to more narrowly focused applications. This approach, exemplified by CoOp-based methods, integrates mutable textual tokens with categorical tokens to foster nuanced textual comprehension. Nonetheless, such specialized textual insights often fail to generalize beyond the scope of familiar categories, as they tend to overshadow the versatile, general textual knowledge intrinsic to the model’s wide-ranging applicability. Addressing this base-novel dilemma, we propose the innovative concept of SparseKnowledge-guided Context Optimization (Sparse-KgCoOp). This technique aims to fortify the adaptable prompts’ capacity to generalize to categories yet unencountered. The cornerstone of Sparse-KgCoOp is based on the premise that reducing the differences between adaptive prompt and their hand-crafted counterparts through sparsification operations can mitigate the erosion of fundamental knowledge. Specifically, Sparse-KgCoOp seeks to narrow the gap between the textual embeddings produced by both the dynamic prompts and the manually devised ones, thus preserving the foundational knowledge while maintaining adaptability. Extensive experiments of several benchmarks demonstrate that the proposed Sparse-KgCoOp is an efficient method for prompt tuning.