Overview

Diffusion guidance studies how to steer a pretrained denoising or flow model during sampling toward a condition or objective, enabling controllable generation and inverse-problem solutions without rebuilding the generator. Common approaches include classifier-free and contrastive score guidance, gradients from rewards, energies, or measurement residuals, and particle or optimization methods; applications range from text-to-image alignment and image restoration to robot motion, molecular design, and safe planning. Recent work also uses adaptive schedules, uncertainty- or geometry-aware corrections, and internal model features to reduce extra evaluations and handle nondifferentiable or spatially localized constraints. A central tension is balancing condition satisfaction against fidelity, diversity, and staying on the learned data manifold, while controlling sensitivity to guidance weights, approximate gradients, and sampling cost.

Latest papers

CardsList

125 papers10 papers in the last four weeks, down 52% on the four weeks before. 0.1% of all new papers.

  1. Diffusion Guidance Is a Controllable Policy Improvement Operator

    May 29, 2025Kevin Frans, Seohong Park, Pieter Abbeel +1Policy LearningOffline RL

  2. Multi-Embodiment Robotic Retargeting via Guided Diffusion Model

    May 27, 2025Zhefeng Cao, Ben Liu, Shunpeng Yang +3Diffusion GuidanceCross-Embodiment Robot Learning

  3. Diffusion-based Evolutionary Optimization for 3D Multi-Objective Molecular Generation

    May 16, 2025Ruiqing Sun, Dawei Feng, Sen Yang +53D Molecular GenerationConstrained Generative Modeling

  4. PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation

    Mar 9, 2025Yanjie Pan, Qingdong He, Zhengkai Jiang +9T2I GenerationControllable Image Generation

  5. ContrastiveCFG: Guiding Diffusion Sampling by Contrasting Positive and Negative Concepts

    Nov 26, 2024Jinho Chang, Changsun Lee, Hyungjin Chung +1Diffusion Model GuidanceClassifier-Free Guidance