解决扩散模型推理时的探索与利用难题，提升生成质量。
Navigating the Exploration-Exploitation Tradeoff in Inference-Time Scaling of Diffusion Models
- 提出漏斗调度与自适应温度策略，优化生成过程
- 在不增加计算量的前提下显著提升样本质量
- 适合追求高质量图像生成的研究者与开发者
推理时缩放在语言模型中取得了显著成功，但在扩散模型中的应用仍不充分。我们观察到，近期基于序列蒙特卡洛（SMC）的方法有效性主要源于对奖励倾斜分布的全局拟合，这天然保留了多模态搜索中的多样性。然而，当前SMC在扩散模型中的应用面临根本性困境：早期噪声样本具有高改进潜力但难以准确评估，而晚期样本虽可可靠评估却几乎不可逆。为应对这一探索-利用权衡问题，我们从搜索算法视角出发，提出两种策略：漏斗调度与自适应温度。这些简单但有效的方案针对扩散模型独特的生成动态与相变行为设计。通过逐步减少维持的粒子数并降低早期奖励影响，我们的方法在不增加噪声函数评估总数的情况下显著提升样本质量。在多个基准和领先文生图扩散模型上的实验表明，该方法优于现有基线。
原文摘要 · Abstract (English)
Inference-time scaling has achieved remarkable success in language models, yet its adaptation to diffusion models remains underexplored. We observe that the efficacy of recent Sequential Monte Carlo (SMC)-based methods largely stems from globally fitting the The reward-tilted distribution, which inherently preserves diversity during multi-modal search. However, current applications of SMC to diffusion models face a fundamental dilemma: early-stage noise samples offer high potential for improvement but are difficult to evaluate accurately, whereas late-stage samples can be reliably assessed but are largely irreversible. To address this exploration-exploitation trade-off, we approach the problem from the perspective of the search algorithm and propose two strategies: Funnel Schedule and Adaptive Temperature. These simple yet effective methods are tailored to the unique generation dynamics and phase-transition behavior of diffusion models. By progressively reducing the number of maintained particles and down-weighting the influence of early-stage rewards, our methods significantly enhance sample quality without increasing the total number of Noise Function Evaluations. Experimental results on multiple benchmarks and state-of-the-art text-to-image diffusion models demonstrate that our approach outperforms previous baselines.
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。