无需训练的树搜索引导，让扩散模型在非可导任务中更可控。
Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Models
- 用树搜索动态生成并筛选候选路径，实现无梯度控制生成。
- 在音乐、分子和DNA设计中分别提升29.01%、16.6%、18.43%。
- 适合需精确控制的离散数据生成，如药物设计与基因编辑。
无训练引导可实现扩散与流模型中的可控生成，但多数方法依赖梯度且假设目标函数可微。本文针对不可微目标与离散数据分布带来的挑战，提出基于树搜索的路径引导方法TreeG，适用于连续与离散场景。TreeG通过在每一步提出、评估并选择候选路径，结合活跃路径上的树搜索与并行探索，构建统一的无训练引导框架。我们系统研究了候选生成模块与评估函数的设计空间，推出了三种新算法。实验表明，TreeG在符号音乐生成、小分子设计与增强子DNA设计任务中均显著优于主流基线，提升幅度分别为29.01%、16.6%与18.43%。此外，我们发现推理时计算量存在可扩展规律，验证了TreeG在推理阶段的高效扩展能力。
原文摘要 · Abstract (English)
Training-free guidance enables controlled generation in diffusion and flow models, but most methods rely on gradients and assume differentiable objectives. This work focuses on training-free guidance addressing challenges from non-differentiable objectives and discrete data distributions. We propose TreeG: Tree Search-Based Path Steering Guidance, applicable to both continuous and discrete settings in diffusion and flow models. TreeG offers a unified framework for training-free guidance by proposing, evaluating, and selecting candidates at each step, enhanced with tree search over active paths and parallel exploration. We comprehensively investigate the design space of TreeG over the candidate proposal module and the evaluation function, instantiating TreeG into three novel algorithms. Our experiments show that TreeG consistently outperforms top guidance baselines in symbolic music generation, small molecule design, and enhancer DNA design with improvements of 29.01%, 16.6%, and 18.43%. Additionally, we identify an inference-time scaling law showing TreeG's scalability in inference-time computation.
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。