HY-WU (第一部分): 一种可扩展的功能性神经记忆框架及其在文本引导图像编辑中的应用
HY-WU (Part I): An Extensible Functional Neural Memory Framework and An Instantiation in Text-Guided Image Editing
AI总结：
提出HY-WU框架，通过功能性神经记忆模块即时生成实例特定权重更新，避免共享权重覆盖导致的干扰，解决持续学习与个性化中的灾难性遗忘问题。
摘要：
基础模型正从离线预测器过渡到期望长时间运行的部署系统。在实际部署中，目标并非固定：领域漂移、用户偏好演变，以及模型发布后出现新任务。这将持续学习和即时个性化从可选功能提升为核心架构要求。然而，大多数适应流程仍遵循静态权重范式：训练后（或任何适应步骤后），推理执行单一参数向量，而不考虑用户意图、领域或实例特定约束。这将训练或适应后的模型视为参数空间中的单个点。在异构且持续演变的机制中，不同目标可能在参数上诱导分离的可行区域，迫使任何单一共享更新陷入妥协、干扰或过度专业化。结果，持续学习和个性化通常实现为对共享权重的重复覆盖，冒着先前学习行为退化的风险。我们提出HY-WU（权重释放），一种记忆优先的适应框架，将适应压力从覆盖单一共享参数点转移。HY-WU将功能性（算子级）记忆实现为神经模块：一个根据实例条件即时合成权重更新的生成器，产生实例特定算子而无需测试时优化。
英文摘要：
Foundation models are transitioning from offline predictors to deployed systems expected to operate over long time horizons. In real deployments, objectives are not fixed: domains drift, user preferences evolve, and new tasks appear after the model has shipped. This elevates continual learning and instant personalization from optional features to core architectural requirements. Yet most adaptation pipelines still follow a static weight paradigm: after training (or after any adaptation step), inference executes a single parameter vector regardless of user intent, domain, or instance-specific constraints. This treats the trained or adapted model as a single point in parameter space. In heterogeneous and continually evolving regimes, distinct objectives can induce separated feasible regions over parameters, forcing any single shared update into compromise, interference, or overspecialization. As a result, continual learning and personalization are often implemented as repeated overwriting of shared weights, risking degradation of previously learned behaviors. We propose HY-WU (Weight Unleashing), a memory-first adaptation framework that shifts adaptation pressure away from overwriting a single shared parameter point. HY-WU implements functional (operator-level) memory as a neural module: a generator that synthesizes weight updates on-the-fly from the instance condition, yielding instance-specific operators without test-time optimization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
