AI 中文总结
针对扩散模型在反馈驱动目标发现中难以探索低似然高价值区域的问题，提出Levy自适应树搜索（LATS）框架，结合重尾探索与树状值反向传播，在保持样本保真度的同时高效发现目标模式，实验验证其显著优于基线。
AI 中文摘要
虽然扩散模型擅长捕捉复杂的数据分布，但科学发现往往需要将生成过程引导至特定的、未被表征的、能够最大化目标函数的区域。这些高价值模式通常位于低似然性的尾部区域，并且只能通过交互式反馈逐步揭示。现有的扩散采样器在此场景下失效：它们继承了预训练模型对高密度区域的偏好，导致稀有但有前景的现象未被充分探索。相反，偏重探索的采样器确保了广泛的覆盖，但在严格的采样预算约束下，无法有效利用高价值模式。为解决这一困境，我们引入了Levy自适应树搜索（LATS），一个用于在线反馈驱动搜索的原则性采样框架。LATS利用重尾探索结合基于树的数值反向传播，逐步发现偏好的模式。通过保持广泛的分布覆盖，LATS成功发现了低似然性、高价值的区域，同时保持了样本保真度和结构多样性。在包括材料科学在内的多个基准测试中的实验表明，LATS在目标发现效率上显著优于基线方法。
英文摘要
While diffusion models excel at capturing complex data distributions, scientific discovery often requires steering generation toward specific, uncharacterized regions that maximize a target objective. These high-utility modes frequently reside in low-likelihood tail regions and are only revealed sequentially through interactive feedback. Existing diffusion samplers fail in this regime: they inherit the pre-trained model's bias toward high-density regions, leaving rare yet promising phenomena underexplored. Conversely, exploration-heavy samplers ensure broad coverage but fail to efficiently exploit high-utility modes when constrained by a strict sampling budget. To resolve this dilemma, we introduce Levy Adaptive Tree Search (LATS), a principled sampling framework for online feedback-driven search. LATS leverages heavy-tailed exploration coupled with tree-based value backpropagation to progressively uncover preferred modes. By maintaining broad distributional coverage, LATS successfully discovers low-likelihood, high-utility regions while preserving sample fidelity and structural diversity. Experiments across diverse benchmarks, including materials science, demonstrate that LATS significantly outperforms baselines in target discovery efficiency.
Comments19 pages, 6 figures, preprint
