research 3D Gaussian Human and Head Avatar Reconstruction Animatable human/head avatar reconstruction and high-fidelity rendering based on 3D Gaussian representations. BSSNet Real-Time Road Scene Semantic Segmentation Real-time semantic segmentation network for road scenes inspired by autoencoder structures. engineering Lightweight LLM Reproduction and Multimodal Extension End-to-end small-parameter LLM training, fine-tuning, RL training, inference, and multimodal extension. Coding Agent Prototype A code-oriented LLM agent with task parsing, context management, tool calling, command execution, verification, and error repair.