English
Related papers

Related papers: Beyond VLM-Based Rewards: Diffusion-Native Latent …

200 papers

Preference optimization for diffusion models aims to align them with human preferences for images. Previous methods typically use Vision-Language Models (VLMs) as pixel-level reward models to approximate human preferences. However, when…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Tao Zhang , Cheng Da , Kun Ding , Huan Yang , Kun Jin , Yan Li , Tingting Gao , Di Zhang , Shiming Xiang , Chunhong Pan

Video diffusion alignment has been heavily relied on scalar rewards. These rewards are typically derived from learned reward models in human preference datasets, requiring additional training and extensive collection. Moreover, scalar…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Yifan Wang , Yanyu Li , Gordon Guocheng Qian , Sergey Tulyakov , Yun Fu , Anil Kag

Current mainstream methods of aligning diffusion models with human preferences typically employ VLM-based reward models. However, these reward models, pre-trained for semantic alignment, struggle to capture the essential perceptual…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Jaxon Zhang , Binxin Yang , Hubery Yin , Chen Li , Jing Lyu

Reinforcement learning (RL) algorithms have been used recently to align diffusion models with downstream objectives such as aesthetic quality and text-image consistency by fine-tuning them to maximize a single reward function under a fixed…

Artificial Intelligence · Computer Science 2026-03-13 Min Cheng , Fatemeh Doudi , Dileep Kalathil , Mohammad Ghavamzadeh , Panganamala R. Kumar

While one commonly trains large diffusion models by collecting datasets on target downstream tasks, it is often desired to align and finetune pretrained diffusion models with some reward functions that are either designed by experts or…

Machine Learning · Computer Science 2025-05-20 Zhen Liu , Tim Z. Xiao , Weiyang Liu , Yoshua Bengio , Dinghuai Zhang

Generating high-quality and photorealistic 3D assets remains a longstanding challenge in 3D vision and computer graphics. Although state-of-the-art generative models, such as diffusion models, have made significant progress in 3D…

Graphics · Computer Science 2025-06-19 Qingming Liu , Zhen Liu , Dinghuai Zhang , Kui Jia

Diffusion models have emerged as powerful generative tools across various domains, yet tailoring pre-trained models to exhibit specific desirable properties remains challenging. While reinforcement learning (RL) offers a promising…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Fengyuan Dai , Zifeng Zhuang , Yufei Huang , Siteng Huang , Bangyan Liao , Donglin Wang , Fajie Yuan

We propose a diffusion-based framework for prompt optimization that leverages Diffusion Language Models (DLMs) to iteratively refine system prompts through masked denoising. By conditioning on interaction traces, including user queries,…

Computation and Language · Computer Science 2026-02-24 Shiyu Wang , Haolin Chen , Liangwei Yang , Jielin Qiu , Rithesh Murthy , Ming Zhu , Zixiang Chen , Silvio Savarese , Caiming Xiong , Shelby Heinecke , Huan Wang

Recent research has shown that fine-tuning diffusion models (DMs) with arbitrary rewards, including non-differentiable ones, is feasible with reinforcement learning (RL) techniques, enabling flexible model alignment. However, applying…

Machine Learning · Computer Science 2025-03-12 Zhiwei Jia , Yuesong Nan , Huixi Zhao , Gengdai Liu

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

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

Reward finetuning has emerged as a promising approach to aligning foundation models with downstream objectives. Remarkable success has been achieved in the language domain by using reinforcement learning (RL) to maximize rewards that…

Machine Learning · Computer Science 2024-03-29 Fei Deng , Qifei Wang , Wei Wei , Matthias Grundmann , Tingbo Hou

The remarkable progress in text-to-video diffusion models enables the generation of photorealistic videos, although the content of these generated videos often includes unnatural movement or deformation, reverse playback, and motionless…

Computer Vision and Pattern Recognition · Computer Science 2025-10-08 Yuta Oshima , Masahiro Suzuki , Yutaka Matsuo , Hiroki Furuta

Aligning text-to-image (T2I) diffusion models with human preferences has emerged as a critical research challenge. While recent advances in this area have extended preference optimization techniques from large language models (LLMs) to the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-25 Junyong Kang , Seohyun Lim , Kyungjune Baek , Hyunjung Shim

Diffusion models achieve state-of-the-art generative performance but are fundamentally bottlenecked by their slow, iterative sampling process. While diffusion distillation techniques enable high-fidelity, few-step generation, traditional…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Linqian Fan , Peiqin Sun , Tiancheng Wen , Shun Lu , Chengru Song

This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions. While diffusion models are widely known to provide excellent generative modeling capability, practical…

Machine Learning · Computer Science 2024-07-19 Masatoshi Uehara , Yulai Zhao , Tommaso Biancalani , Sergey Levine

Preference optimization has emerged as an efficient alternative to online reinforcement learning from human feedback (RLHF) for aligning text-to-image diffusion models. However, existing methods largely reduce supervision to binary pairwise…

Machine Learning · Computer Science 2026-05-27 Austin Wang , Jiaqi Han , Stefano Ermon , Yisong Yue

Reinforcement learning from human feedback (RLHF) has been popular for aligning text-to-image (T2I) diffusion models with human preferences. As a mainstream branch of RLHF, Direct Preference Optimization (DPO) offers a computationally…

Machine Learning · Computer Science 2026-05-07 Jiaming Hu , Jiamu Bai , Haoyu Wang , Debarghya Mukherjee , Ioannis Ch. Paschalidis

For practical use, diffusion- or flow-based generative models must be aligned with task-specific rewards, such as prompt fidelity or aesthetic preference. That alignment is challenging because the reward is defined for clean output images,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Hyojun Go , Hyungjin Chung , Prune Truong , Goutam Bhat , Li Mi , Zhaochong An , Zixiang Zhao , Dominik Narnhofer , Serge Belongie , Federico Tombari , Konrad Schindler

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
‹ Prev 1 2 3 10 Next ›