Diffusion Alignment

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 65

All topics

Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models
Mar 15, 2026Niklas Schweiger, Daniel Cremers, Karnik RamDiffusion Alignment Generative Flow Networks
Technical University of Munich, Germany · Munich Center for Machine Learning, Germany
Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision
Dec 29, 2025Dohyun Kim, Seungwoo Lyu, Seung Wook Kim +1Diffusion Alignment Backtranslation Augmented Direct Preference Optimization
Dept. of CSE, Korea University · 2NVIDIA
Multi-dimensional Preference Alignment by Conditioning Reward Itself
Dec 11, 2025Jiho Jang, Jinyoung Kim, Kyungjune Baek +1Diffusion Alignment Backtranslation Augmented Direct Preference Optimization
Seoul National University · Sejong University
Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation
Nov 25, 2025Taehoon Kim, Henry Gouk, Timothy HospedalesDiffusion Alignment Text-To-Image Diffusion Models
School of Informatics, University of Edinburgh · 2Samsung AI Center, Cambridge
ELBO-T2IAlign: A Generic ELBO-Based Method for Calibrating Pixel-level Text-Image Alignment in Diffusion Models
Jun 11, 2025Qin Zhou, Zhiyang Zhang, Jinglong Wang +5Image-Text Alignment Diffusion Alignment
School of Software, Beihang University, Beijing 100191, China · College of Computer and Cyber Security, Hebei Normal University, Hebei 050024, China · Department of Computer Science, The University of Hong Kong, Hong Kong

Mar 15, 2026, cs.LGJ/K move · Enter open · S save

Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models

Niklas Schweiger, Daniel Cremers, Karnik Ram

Technical University of Munich, Germany · Munich Center for Machine Learning, Germany

Diffusion Alignment Generative Flow Networks Generative Models Flow Models Trust Region

Open paper AskPDF arXiv

Optimizing the noise samples of diffusion and flow models is an increasingly popular approach to align these models to target rewards at inference time. However, we observe that these approaches are usually restricted to differentiable or cheap reward models, the formulation of the underlying pretrained generative model, or are memory/compute inefficient. We instead propose a simple trust-region based search algorithm (TRS) which treats the pre-trained generative and reward models as a black-box and only optimizes the source noise. Our approach achieves a good balance between global exploration and local exploitation, and is versatile and easily adaptable to various generative settings and reward models with minimal hyperparameter tuning. We evaluate TRS across text-to-image, molecule and protein design tasks, and obtain significantly improved output samples over the base generative models and other inference-time alignment approaches which optimize the source noise sample, or even the entire reverse-time sampling noise trajectories in the case of diffusion models. Our source code is publicly available.

Momentum

Related topics

Latest papers 65

Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models

Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision

Multi-dimensional Preference Alignment by Conditioning Reward Itself

Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation

ELBO-T2IAlign: A Generic ELBO-Based Method for Calibrating Pixel-level Text-Image Alignment in Diffusion Models