根据任务难度动态调整生成计算量，提升效率与效果。
Adaptive Inference-Time Scaling via Cyclic Diffusion Search
- 用双向循环扩散搜索自适应调节推理过程
- 在多个任务上实现性能提升且计算开销可控
- 适合需要灵活资源分配的生成式应用
扩散模型在图像合成到复杂推理等任务中展现出强大生成能力。然而，大多数推理阶段的计算扩展方法依赖固定去噪流程，难以根据实例难度或任务需求动态分配计算资源。本文提出自适应推理阶段扩展问题，并引入自适应双向循环扩散（ABCD）框架，通过双向扩散循环优化输出，同时自适应控制探索深度与终止时机。该框架包含三个组件：循环扩散搜索、自动探索-利用平衡机制以及自适应思考时间。实验表明，ABCD在多种任务中均能提升性能，同时保持计算高效性。
原文摘要 · Abstract (English)
Diffusion models have demonstrated strong generative capabilities across domains ranging from image synthesis to complex reasoning tasks. However, most inference-time scaling methods rely on fixed denoising schedules, limiting their ability to allocate computation based on instance difficulty or task-specific demands adaptively. We introduce the challenge of adaptive inference-time scaling-dynamically adjusting computational effort during inference-and propose Adaptive Bi-directional Cyclic Diffusion (ABCD), a flexible, search-based inference framework. ABCD refines outputs through bi-directional diffusion cycles while adaptively controlling exploration depth and termination. It comprises three components: Cyclic Diffusion Search, Automatic Exploration-Exploitation Balancing, and Adaptive Thinking Time. Experiments show that ABCD improves performance across diverse tasks while maintaining computational efficiency.
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。