用低秩适配器让模型权重具备语义结构，提升生成质量
Weight Space Representation Learning via Neural Field Adaptation
- 通过预训练模型和乘法型LoRA约束权重空间，诱导结构化表示
- 在2D/3D重建与生成任务中，权重表示质量高且具语义区分性
- 与扩散模型结合时，生成效果优于现有权重空间方法
我们探索权重作为有效表示的潜力，聚焦于神经场。核心洞察是：通过预训练基础模型与低秩适配（LoRA）约束优化空间，可在权重空间中诱导出结构。在2D和3D数据的重建、生成与分析任务中，乘法型LoRA权重展现出高表示质量、显著性和语义结构。当与潜在扩散模型结合时，其生成质量高于现有权重空间方法。
原文摘要 · Abstract (English)
We investigate the potential of weights to serve as effective representations, focusing on neural fields. Our key insight is that constraining the optimization space through a pre-trained base model and low-rank adaptation (LoRA) can induce structure in weight space. Across reconstruction, generation, and analysis tasks on 2D and 3D data, we find that multiplicative LoRA weights achieve high representation quality while exhibiting distinctiveness and semantic structure. When used with latent diffusion models, multiplicative LoRA weights enable higher-quality generation than existing weight-space methods.
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。