{"ID":2829561,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.12339","arxiv_id":"2512.12339","title":"Unified Control for Inference-Time Guidance of Denoising Diffusion Models","abstract":"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","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2512.12339","url_pdf":"https://arxiv.org/pdf/2512.12339v1","authors":"[\"Maurya Goyal\",\"Anuj Singh\",\"Hadi Jamali-Rad\"]","published":"2025-12-13T14:12:10Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":605958,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2829561,"paper_url":"https://arxiv.org/abs/2512.12339","paper_title":"Unified Control for Inference-Time Guidance of Denoising Diffusion Models","repo_url":"https://github.com/maurya-goyal10/UniCoDe","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}