Complete supplementary package for: "VDLF-Net: Variational Feature Fusion for Adaptive and Few-Shot Visual Learning" Author: Jiawei Yan, Department of Statistics, School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai 200240, ChinaContact: yjw1998@sjtu.edu.cn ----------------------------------------------------------------Contents (vdlf_net.zip)----------------------------------------------------------------Unpack to folder vdlf_net/ with five parts: • exp1codes/ — Main Experiment 1 code, notebooks, CSV results, and notes (start here).• experiment_1/ — Earlier Experiment 1 tree (CIFAR-100; legacy copy).• experiment_2/ — Few-shot experiments on Mini-ImageNet (code, logs, figures, data/, checkpoints).• experiment_ablation/ — Ablation studies (scripts, CSV, notebooks, checkpoints).• tSNE/ — t-SNE scripts and figure outputs. Also includes Markdown guides, shell scripts, and result files (CSV/JSON/TXT) where applicable. ----------------------------------------------------------------Reproduction----------------------------------------------------------------Python 3.10+; PyTorch/torchvision (CUDA as appropriate). See README and guides inside each folder. ----------------------------------------------------------------Version----------------------------------------------------------------This deposit (June 2026) supersedes the Zenodo record "Supplementary archive: VDLF-Net (code, data, and results)" (April 2026, v1). Please use this DOI for the current manuscript. License: CC BY 4.0. Please cite this Zenodo DOI together with the journal article when published.