统一融合采样与梯度引导，提升扩散模型生成效率与对齐精度。
Unified Control for Inference-Time Guidance of Denoising Diffusion Models
- 提出统一框架UniCoDe，结合采样与梯度信号优化生成过程。
- 在多任务上优于或媲美当前最优基线，兼顾奖励对齐与先验偏离。
- 适合需高效生成且要求输出精准对齐任务的研究者使用。
将扩散模型输出与下游目标对齐对于提升特定任务性能至关重要。目前，无需训练的推理阶段方法主要分为两类：基于采样的方法通过探索多个候选输出并选择奖励信号更高的结果；梯度引导方法则利用可微分奖励近似直接引导生成过程。本文提出通用算法UniCoDe，将采样与梯度引导的优势整合到统一框架中。UniCoDe在采样过程中融入局部梯度信号，缓解了复杂奖励驱动采样方法固有的低效问题。通过协同结合两种范式，UniCoDe实现了更高效的采样，并在奖励对齐与扩散模型无条件先验偏离之间取得更好平衡。实验表明，UniCoDe在多个任务上保持与最先进基线相当的性能。代码已公开于https://github.com/maurya-goyal10/UniCoDe。
原文摘要 · Abstract (English)
Aligning diffusion model outputs with downstream objectives is essential for improving task-specific performance. Broadly, inference-time training-free approaches for aligning diffusion models can be categorized into two main strategies: sampling-based methods, which explore multiple candidate outputs and select those with higher reward signals, and gradient-guided methods, which use differentiable reward approximations to directly steer the generation process. In this work, we propose a universal algorithm, UniCoDe, which brings together the strengths of sampling and gradient-based guidance into a unified framework. UniCoDe integrates local gradient signals during sampling, thereby addressing the sampling inefficiency inherent in complex reward-based sampling approaches. By cohesively combining these two paradigms, UniCoDe enables more efficient sampling while offering better trade-offs between reward alignment and divergence from the diffusion unconditional prior. Empirical results demonstrate that UniCoDe remains competitive with state-of-the-art baselines across a range of tasks. The code is available at https://github.com/maurya-goyal10/UniCoDe
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。