HY-WU（上篇）：可扩展功能性神经记忆框架及其在文本引导图像编辑中的实例化

HY-WU (Part I): An Extensible Functional Neural Memory Framework and An Instantiation in Text-Guided Image Editing

March 7, 2026

作者: Tencent HY Team

cs.AI

摘要

基础模型正从离线预测器转变为需长期运行的部署系统。在实际部署中，目标并非固定不变：数据分布会漂移、用户偏好会演变、新任务会在模型发布后不断涌现。这使得持续学习与即时个性化从可选特性升级为核心架构需求。然而当前大多数适配流程仍遵循静态权重范式：在训练（或任何适配步骤）完成后，无论用户意图、领域或实例特定约束如何，推理过程都执行单一参数向量。这种范式将训练或适配后的模型视为参数空间中的单个点。在异构且持续演化的场景中，不同目标会在参数空间形成相互分离的可行域，迫使任何共享更新陷入折衷、干扰或过度专业化。因此，持续学习与个性化常通过重复覆写共享权重来实现，这可能导致已习得能力的退化。我们提出HY-WU（权重释放）这一内存优先的适配框架，将适配压力从覆写单一共享参数点转移至功能化内存系统。HY-WU通过神经模块实现算子级功能内存：该生成器能根据实例条件动态合成权重更新，无需测试时优化即可生成实例特定算子。

English

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.