paper-with-me

Papers

Conditional Diffusion with Less Explicit Guidance via Model Predictive Control

2022-10-21 · Max W. Shen, Ehsan Hajiramezanali, Gabriele Scalia, Alex Tseng, Nathaniel Diamant, Tommaso Biancalani, Andreas Loukas

How much explicit guidance is necessary for conditional diffusion? We consider the problem of conditional sampling using an unconditional diffusion model and limited explicit guidance (e.g., a noised classifier, or a conditional diffusion model) that is restricted to a small number of time steps. We explore a model predictive control (MPC)-like approach to approximate guidance by simulating unconditional diffusion forward, and backpropagating explicit guidance feedback. MPC-approximated guides have high cosine similarity to real guides, even over large simulation distances. Adding MPC steps improves generative quality when explicit guidance is limited to five time steps.

📄 PDF Abstract BibTeX arXiv:2210.12192

Code (0)

등록된 구현이 없습니다.

Tasks

Model Predictive Control

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…

Similar Papers 제목 키워드 기반

Robust Guided Diffusion for Offline Black-Box Optimization

2024-10-01 · Can Sam Chen, Christopher Beckham, Zixuan Liu, Xue Liu 외

Offline black-box optimization aims to maximize a black-box function using an offline dataset of designs and their measured properties. Two main approaches have emerged: the forward approach, which learns a mapping from …

Guidance Free Image Editing via Explicit Conditioning

2025-03-22 · Mehdi Noroozi, Alberto Gil Ramos, Luca Morreale, Ruchika Chavhan 외

Current sampling mechanisms for conditional diffusion models rely mainly on Classifier Free Guidance (CFG) to generate high-quality images. However, CFG requires several denoising passes in each time step, e.g., up to th…

Denoising

Chemistry-Inspired Diffusion with Non-Differentiable Guidance

2024-10-09 · Yuchen Shen, Chenhao Zhang, Sijie Fu, Chenghui Zhou 외

Recent advances in diffusion models have shown remarkable potential in the conditional generation of novel molecules. These models can be guided in two ways: (i) explicitly, through additional features representing the c…

Atomic Forces

Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis Approach

2026-02-05 · Zhengyi Guo, Wenpin Tang, Renyuan Xu arxiv

We study conditional generation in diffusion models under hard constraints, where generated samples must satisfy prescribed events with probability one. Such constraints arise naturally in safety-critical applications an…

Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models

2026-05-29 · Shreyansh Modi, Akshat Tomar, Aarush Aggarwal arxiv

Unconditional diffusion models offer powerful generative priors, yet steering them toward aesthetically enhanced outputs remains largely unexplored. We show that h-space patching, the dominant paradigm for training-free …