English
Related papers

Related papers: Test-time Alignment of Diffusion Models without Re…

200 papers

This tutorial provides an in-depth guide on inference-time guidance and alignment methods for optimizing downstream reward functions in diffusion models. While diffusion models are renowned for their generative modeling capabilities,…

Artificial Intelligence · Computer Science 2025-01-22 Masatoshi Uehara , Yulai Zhao , Chenyu Wang , Xiner Li , Aviv Regev , Sergey Levine , Tommaso Biancalani

Discrete diffusion models have become highly effective across various domains. However, real-world applications often require the generative process to adhere to certain constraints. To this end, we propose a Sequential Monte Carlo (SMC)…

Machine Learning · Computer Science 2026-03-17 Zijing Ou , Chinmay Pani , Yingzhen Li

Adapting a pretrained diffusion model to new objectives at inference time remains an open problem in generative modeling. Existing steering methods suffer from inaccurate value estimation, especially at high noise levels, which biases…

Machine Learning · Computer Science 2025-06-27 Vineet Jain , Kusha Sareen , Mohammad Pedramfar , Siamak Ravanbakhsh

We study inference-time alignment for diffusion-based generative models, aiming to steer a base model toward high-reward outputs without updating its weights. Recent Sequential Monte Carlo (SMC)-based steering methods approximate…

Machine Learning · Computer Science 2026-05-26 Weixin Wang , Yu Yang , Wei Deng , Pan Xu

Inference-time scaling has achieved remarkable success in language models, yet its adaptation to diffusion models remains underexplored. We observe that the efficacy of recent Sequential Monte Carlo (SMC)-based methods largely stems from…

Machine Learning · Computer Science 2025-08-19 Xun Su , Jianming Huang , Yang Yusen , Zhongxi Fang , Hiroyuki Kasai

Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-trained generative models to maximize a given reward function,…

Machine Learning · Statistics 2026-02-03 Yidong Ouyang , Liyan Xie , Hongyuan Zha , Guang Cheng

Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model. Although existing methods are derived from different perspectives, we show…

Machine Learning · Computer Science 2026-05-08 Jeongjae Lee , Jinho Chang , Jeongsol Kim , Jong Chul Ye

Diffusion-based planning, learning, and control methods present a promising branch of powerful and expressive decision-making solutions. Given the growing interest, such methods have undergone numerous refinements over the past years.…

Machine Learning · Computer Science 2025-02-19 Dom Huh , Prasant Mohapatra

Aligning diffusion models with user preferences has been a key challenge. Existing methods for aligning diffusion models either require retraining or are limited to differentiable reward functions. To address these limitations, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Po-Hung Yeh , Kuang-Huei Lee , Jun-Cheng Chen

Discrete diffusion models have recently emerged as a powerful class of generative models for chemistry and biology data. In these fields, the goal is to generate various samples with high rewards (e.g., drug-likeness in molecules), making…

Machine Learning · Computer Science 2026-02-11 Prin Phunyaphibarn , Minhyuk Sung

Discrete diffusion models have recently emerged as a promising alternative to the autoregressive approach for generating discrete sequences. Sample generation via gradual denoising or demasking processes allows them to capture hierarchical…

In this work, we focus on the alignment problem of diffusion models with a continuous reward function, which represents specific objectives for downstream tasks, such as increasing darkness or improving the aesthetics of images. The central…

Machine Learning · Computer Science 2024-10-03 Zhiwei Tang , Jiangweizhi Peng , Jiasheng Tang , Mingyi Hong , Fan Wang , Tsung-Hui Chang

We propose a novel sequential Monte Carlo (SMC) method for sampling from unnormalized target distributions based on a reverse denoising diffusion process. While recent diffusion-based samplers simulate the reverse diffusion using…

Computation · Statistics 2025-11-06 Luhuan Wu , Yi Han , Christian A. Naesseth , John P. Cunningham

We address the problem of accurate, training-free guidance for conditional generation in trained diffusion models. Existing methods typically rely on point-estimates to approximate the posterior score, often resulting in biased…

Machine Learning · Statistics 2026-01-30 Aidan Gleich , Scott C. Schmidler

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-aligned samples at…

Machine Learning · Computer Science 2026-05-22 Kushagra Pandey , Farrin Marouf Sofian , Jan Niklas Groeneveld , Felix Draxler , Stephan Mandt

We study the problem of training diffusion and flow generative models to sample from target distributions defined by an exponential tilting of a base density; a formulation that subsumes both sampling from unnormalized densities and reward…

Machine Learning · Statistics 2026-05-04 Carles Domingo-Enrich , Yuanqi Du , Michael S. Albergo

Test-time scaling through reward-guided generation remains largely unexplored for discrete diffusion models despite its potential as a promising alternative. In this work, we introduce Iterative Reward-Guided Refinement (IterRef), a novel…

Machine Learning · Computer Science 2025-11-11 Sanghyun Lee , Sunwoo Kim , Seungryong Kim , Jongho Park , Dongmin Park

Discrete diffusion models have emerged as powerful frameworks for generating structured categorical data. However, efficiently sampling from reward-tilted distributions remains a fundamental challenge. While Twisted Sequential Monte Carlo…

Machine Learning · Computer Science 2026-05-25 Jaihoon Kim , Taehoon Yoon , Prin Phunyaphibarn , Seungjun Kim , Morteza Mardani , Minhyuk Sung

Diffusion models have shown promising generative capabilities across diverse domains, yet aligning their outputs with desired reward functions remains a challenge, particularly in cases where reward functions are non-differentiable. Some…

Machine Learning · Computer Science 2025-06-04 Xiner Li , Masatoshi Uehara , Xingyu Su , Gabriele Scalia , Tommaso Biancalani , Aviv Regev , Sergey Levine , Shuiwang Ji

This work presents self-rewarding sequential Monte Carlo (SMC), an inference-time scaling algorithm enabling effective sampling of masked diffusion language models (MDLMs). Our algorithm stems from the observation that most existing MDLMs…

Machine Learning · Computer Science 2026-02-03 Ziwei Luo , Ziqi Jin , Lei Wang , Lidong Bing , Thomas B. Schön
‹ Prev 1 2 3 10 Next ›