Infrared small target detection (ISTD) is challenging due to complex backgrounds, low signal-to-clutter ratios (SCRs), and varying target sizes and shapes. Effective detection relies on capturing local contextual information at the appropriate scale. However, small-kernel CNNs have limited receptive fields, leading to false alarms, while transformer models, with global receptive fields, often treat small targets as noise, resulting in miss-detections. Hybrid models struggle to bridge the semantic gap between convolutional neural networks (CNNs) and transformers, causing high complexity. To address these challenges, we propose learning dynamic local context representations network (LCRNet), a novel method that learns dynamic local context representations for ISTD. The model consists of three components: 1) coarse-to-fine convolution block (C2FBlock), inspired by partial differential equation (PDE) solvers, for efficient small target information capture; 2) dynamic local context attention (DLC-Attention), a large-kernel attention mechanism that dynamically builds context and reduces feature redundancy; and 3) hierarchical large-kernel convolution (HLKConv), a hierarchical convolution operator based on large-kernel decomposition that preserves sparsity and mitigates the drawbacks of dilated convolutions. Despite its simplicity, with only 1.65 M parameters, LCRNet achieves state-of-the-art (SOTA) performance. Experiments on multiple datasets, comparing LCRNet with 33 SOTA methods, demonstrate its superior performance and efficiency. Specifically, our method achieves an nIoU exceeding 70% for small object segmentation on the highly challenging IRSTD-1k dataset. Website: https://github.com/HaLongbao/LCRNet/