English
Related papers

Related papers: Iterative Tilting for Diffusion Fine-Tuning

200 papers

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

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

This paper proposes an extension to discrete Phase-Type distributions (DPH) by introducing random rewards. These allow for modeling a system in which a visit to a certain state does not emit a deterministic reward. Instead, the rewards…

Methodology · Statistics 2026-04-22 Simon Pauli , Andreas Futschik

Text-to-motion generation, which synthesizes 3D human motions from text inputs, holds immense potential for applications in gaming, film, and robotics. Recently, diffusion-based methods have been shown to generate more diversity and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Wanjiang Weng , Xiaofeng Tan , Junbo Wang , Guo-Sen Xie , Pan Zhou , Hongsong Wang

Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains challenging. We propose Reward-Tilted Distribution Matching Distillation (RTDMD), a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Yushi Huang , Xiangxin Zhou , Ruoyu Wang , Chi Zhang , Jun Zhang , Tianyu Pang

Diffusion models excel at capturing complex data distributions, such as those of natural images and proteins. While diffusion models are trained to represent the distribution in the training dataset, we often are more concerned with other…

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

Learning from feedback has been shown to enhance the alignment between text prompts and images in text-to-image diffusion models. However, due to the lack of focus in feedback content, especially regarding the object type and quantity,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Xuexiang Niu , Jinping Tang , Lei Wang , Ge Zhu

Diffusion alignment aims to optimize diffusion models for the downstream objective. While existing methods based on reinforcement learning or direct backpropagation achieve considerable success in maximizing rewards, they often suffer from…

Machine Learning · Computer Science 2026-03-09 Jaewoo Lee , Minsu Kim , Sanghyeok Choi , Inhyuck Song , Sujin Yun , Hyeongyu Kang , Woocheol Shin , Taeyoung Yun , Kiyoung Om , Jinkyoo Park

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

Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approaches. However, applying supervised fine-tuning (SFT) to diffusion models remains…

Computation and Language · Computer Science 2026-05-12 Guowei Xu , Wenxin Xu , Jiawang Zhao , Kaisheng Ma

We introduce RewardFlow, an inversion-free framework that steers pretrained diffusion and flow-matching models at inference time through multi-reward Langevin dynamics. RewardFlow unifies complementary differentiable rewards for semantic…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Onkar Susladkar , Dong-Hwan Jang , Tushar Prakash , Adheesh Juvekar , Vedant Shah , Ayush Barik , Nabeel Bashir , Muntasir Wahed , Ritish Shrirao , Ismini Lourentzou

Diffusion models excel at capturing the natural design spaces of images, molecules, DNA, RNA, and protein sequences. However, rather than merely generating designs that are natural, we often aim to optimize downstream reward functions while…

Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models with human preferences, inspiring the development of reward-centric diffusion reinforcement learning (RDRL) to achieve similar…

Machine Learning · Computer Science 2026-03-24 Kwanyoung Kim , Byeongsu Sim

Reinforcement learning fine-tuning has become the dominant approach for aligning diffusion models with human preferences. However, assessing images is intrinsically a multi-dimensional task, and multiple evaluation criteria need to be…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Canyu Zhao , Hao Chen , Yunze Tong , Yu Qiao , Jiacheng Li , Chunhua Shen

Recent advances in denoising diffusion models have enabled rapid generation of optimized structures for topology optimization. However, these models often rely on surrogate predictors to enforce physical constraints, which may fail to…

Machine Learning · Computer Science 2025-08-05 Euihyun Kim , Keun Park , Yeoneung Kim

Discrete diffusion models have recently gained significant attention due to their ability to process complex discrete structures for language modeling. However, fine-tuning these models with policy gradient methods, as is commonly done in…

Machine Learning · Statistics 2025-12-19 Oussama Zekri , Nicolas Boullé

Image tiling -- the seamless connection of disparate images to create a coherent visual field -- is crucial for applications such as texture creation, video game asset development, and digital art. Traditionally, tiles have been constructed…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Or Madar , Ohad Fried

Diffusion models have achieved remarkable results in image generation, and have similarly been used to learn high-performing policies in sequential decision-making tasks. Decision-making diffusion models can be trained on lower-quality…

Machine Learning · Computer Science 2023-12-12 Felipe Nuti , Tim Franzmeyer , João F. Henriques

Self-rewarding have emerged recently as a powerful tool in the field of Natural Language Processing (NLP), allowing language models to generate high-quality relevant responses by providing their own rewards during training. This innovative…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Safouane El Ghazouali , Arnaud Gucciardi , Umberto Michelucci