paper-with-me

Papers

Variational Control for Guidance in Diffusion Models

2025-02-06 · Kushagra Pandey, Farrin Marouf Sofian, Felix Draxler, Theofanis Karaletsos, Stephan Mandt

Diffusion models exhibit excellent sample quality, but existing guidance methods often require additional model training or are limited to specific tasks. We revisit guidance in diffusion models from the perspective of variational inference and control, introducing Diffusion Trajectory Matching (DTM) that enables guiding pretrained diffusion trajectories to satisfy a terminal cost. DTM unifies a broad class of guidance methods and enables novel instantiations. We introduce a new method within this framework that achieves state-of-the-art results on several linear, non-linear, and blind inverse problems without requiring additional model training or specificity to pixel or latent space diffusion models. Our code will be available at https://github.com/czi-ai/oc-guidance

📄 PDF Abstract BibTeX arXiv:2502.03686

Code (1)

czi-ai/oc-guidance 공식 구현 pytorch

Tasks

SpecificityVariational Inference

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

Simple Guidance Mechanisms for Discrete Diffusion Models

2024-12-13 · Yair Schiff, Subham Sekhar Sahoo, Hao Phung, Guanghan Wang 외

Diffusion models for continuous data gained widespread adoption owing to their high quality generation and control mechanisms. However, controllable diffusion on discrete data faces challenges given that continuous guida…

Image Generation

Inference-Time Alignment for Diffusion Models via Variationally Stable Doob's Matching

2026-01-10 · Jinyuan Chang, Chenguang Duan, Yuling Jiao, Yi Xu 외 arxiv

Inference-time alignment for diffusion models aims to adapt a pre-trained reference diffusion model toward a target distribution without retraining the reference score network, thereby preserving the generative capacity …

Stein Diffusion Guidance: Training-Free Posterior Correction for Sampling Beyond High-Density Regions

2025-07-07 · Van Khoa Nguyen, Lionel Blondé, Alexandros Kalousis arxiv

Training-free diffusion guidance offers a flexible framework for leveraging off-the-shelf classifiers without additional training. Yet, current approaches hinge on posterior approximations via Tweedie's formula, which of…

Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit Correction

2026-06-04 · Hongkun Dou, Zike Chen, Fengji Li, Hongjue Li 외 arxiv

Controllable generation with discrete diffusion models is often hindered by high computational overhead or the need for retraining. In this paper, we present \underline{\textbf{G}}radient-\underline{\textbf{I}}nformed \u…

Hierarchical Variational Policies for Reward-Guided Diffusion

2026-05-20 · Kushagra Pandey, Farrin Marouf Sofian, Jan Niklas Groeneveld, Felix Draxler 외 arxiv

Adapting pretrained diffusion models to downstream objectives such as inverse problems often requires expensive test-time guidance or optimization. We propose a principled framework for generating high-quality reward-ali…

Test-time Adaptation