解决生成个性化中的语义坍缩问题，提升提示词忠实度。
Adaptive Subspace Projection for Generative Personalization
- 通过自适应子空间投影，精准定位并修正语义漂移。
- 在不训练的前提下，显著提升提示词与上下文的匹配度。
- 适合需要高保真个性化生成的场景，如图像定制。
生成式个性化常面临语义坍缩问题（SCP），即学习到的个性化概念会覆盖文本提示的其他内容，导致模型忽略重要上下文。我们分析发现，造成SCP的语义漂移并非随机，而是集中在特定低维子空间中。同时，个性化过程会扰动原始基础概念的嵌入，使其成为不稳定的参考点。基于此，我们提出测试时嵌入调整的自适应子空间投影（AdaptSP），一种无需训练的方法，以预训练的稳定嵌入为锚点，将语义漂移隔离并投影至识别出的子空间，实现精确调整，缓解SCP同时保持主体身份。实验表明，该方法显著提升提示词保真度与上下文一致性。
原文摘要 · Abstract (English)
Generative personalization often suffers from the semantic collapsing problem (SCP), where a learned personalized concept overpowers the rest of the text prompt, causing the model to ignore important contextual details. To address this, we first analyze the underlying cause, revealing that the semantic drift responsible for SCP is not random but is concentrated within a specific low-dimensional subspace. We also discover that the personalization process perturbs the embedding of the original base concept, making it an unstable reference point. Based on these insights, we introduce Test-time Embedding Adjustment with Adaptive Subspace Projection (AdaptSP), a training-free method that uses the stable, pre-trained embedding as an anchor. AdaptSP isolates the semantic drift and projects it onto the identified subspace, performing a precise adjustment that mitigates SCP while maintaining the subject identity. Our experiments show that this targeted approach significantly improves prompt fidelity and contextual alignment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。