Pest detection is a challenging task due to the high visual similarity between species, their dense distribution in fields, and complex agricultural backgrounds. Existing models often have large parameter sizes, making them unsuitable for deployment on resource-constrained devices commonly used in agriculture. Achieving a balance between detection accuracy and computational efficiency remains a key challenge. In this paper, we propose LitePest, a lightweight and efficient pest detection model designed to improve accuracy while significantly reducing model complexity and computational requirements. LitePest introduces the innovative Lightweight Long-Range Aggregation Network, which minimizes model parameters and computational load by reducing redundant feature computations through a novel partial convolution based on a gradient importance channel selection strategy. Additionally, LitePest features a novel neck architecture to enhance spatial resolution and semantic richness, along with the MPDIoU loss function for improved small-target detection. Extensive experiments on the Pest24 dataset demonstrate that LitePest achieves superior performance in balancing lightweight design and detection accuracy, surpassing existing methods on the Pest24 dataset.

Large Language Models (LLMs) have shown significant potential in recommendation systems by enhancing the semantic reasoning capabilities derived from user-item interactions. However, existing methods often rely on original reviews as ground truth explanations, with limited attention to uncovering the underlying rationales behind each interaction, which hampers the reasoning performance of LLMs. In this paper, we propose a novel Hierarchical Distillation for Recommendation (HDRec) model that effectively specifies user and item profiles by hierarchically distilling interaction rationales from reviews using LLMs. Additionally, we introduce a review summary task that condenses distilled information, such as user preferences, personality traits, item attributes, and target audience, improving both model training and interpretability. Extensive experiments demonstrate that HDRec achieves state-of-the-art performance on three real-world datasets in both sequential and Top-N recommendation tasks. The source code for HDRec is publicly available at https://github.com/linglingl635/HDRec.