English
Related papers

Related papers: Do Less, Achieve More: Do We Need Every-Step Optim…

200 papers

We investigate a general approach for improving user prompts in text-to-image (T2I) diffusion models by finding prompts that maximize a reward function specified at test-time. Although diverse reward models are used for evaluating image…

Machine Learning · Computer Science 2025-09-30 Semin Kim , Yeonwoo Cha , Jaehoon Yoo , Seunghoon Hong

Large Language Models (LLMs) can perform many NLP tasks well, but fully fine-tuning them is expensive and requires a lot of memory. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA reduce this cost by adding small low-rank…

Machine Learning · Computer Science 2025-12-19 Anshul Kumar , Gagan Raj Gupta , Manisha Chawla

Diffusion models have become a central paradigm for image and multimodal generation, yet their deployment raises persistent questions about alignment, safety, preference satisfaction, and robustness to misuse. This survey reviews recent…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Preeti Lamba , Kiran Ravish , Ankita Kushwaha , Pawan Kumar

Reinforcement learning from human feedback (RLHF), which aligns a diffusion model with input prompt, has become a crucial step in building reliable generative AI models. Most works in this area use a discrete-time formulation, which is…

Machine Learning · Computer Science 2025-08-25 Hanyang Zhao , Haoxian Chen , Ji Zhang , David D. Yao , Wenpin Tang

Fine-tuning Diffusion Models remains an underexplored frontier in generative artificial intelligence (GenAI), especially when compared with the remarkable progress made in fine-tuning Large Language Models (LLMs). While cutting-edge…

Machine Learning · Computer Science 2024-02-16 Huizhuo Yuan , Zixiang Chen , Kaixuan Ji , Quanquan Gu

There has been significant progress in deep reinforcement learning (RL) in recent years. Nevertheless, finding suitable hyperparameter configurations and reward functions remains challenging even for experts, and performance heavily relies…

Machine Learning · Computer Science 2024-10-10 Julian Dierkes , Emma Cramer , Holger H. Hoos , Sebastian Trimpe

Denoising-based generative models, particularly diffusion and flow matching algorithms, have achieved remarkable success. However, aligning their output distributions with complex downstream objectives, such as human preferences,…

Machine Learning · Computer Science 2025-08-29 Luozhijie Jin , Zijie Qiu , Jie Liu , Zijie Diao , Lifeng Qiao , Ning Ding , Alex Lamb , Xipeng Qiu

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

Distribution Matching Distillation (DMD) facilitates efficient inference by distilling multi-step diffusion models into few-step variants. Concurrently, Reinforcement Learning (RL) has emerged as a vital tool for aligning generative models…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Dengyang Jiang , Dongyang Liu , Zanyi Wang , Qilong Wu , Liuzhuozheng Li , Hengzhuang Li , Xin Jin , David Liu , Changsheng Lu , Zhen Li , Bo Zhang , Mengmeng Wang , Steven Hoi , Peng Gao , Harry Yang

One of the main goals of reinforcement learning (RL) is to provide a~way for physical machines to learn optimal behavior instead of being programmed. However, effective control of the machines usually requires fine time discretization. The…

Machine Learning · Computer Science 2022-07-12 Jakub Łyskawa , Paweł Wawrzyński

Text-to-image diffusion models are a class of deep generative models that have demonstrated an impressive capacity for high-quality image generation. However, these models are susceptible to implicit biases that arise from web-scale…

Computer Vision and Pattern Recognition · Computer Science 2024-01-24 Yinan Zhang , Eric Tzeng , Yilun Du , Dmitry Kislyuk

Preference alignment in diffusion models has primarily focused on benign human preferences (e.g., aesthetic). In this paper, we propose a novel perspective: framing unrestricted adversarial example generation as a problem of aligning with…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Kaixun Jiang , Zhaoyu Chen , Haijing Guo , Jinglun Li , Jiyuan Fu , Pinxue Guo , Hao Tang , Bo Li , Wenqiang Zhang

Reinforcement learning for training end-to-end autonomous driving models in closed-loop simulations is gaining growing attention. However, most simulation environments differ significantly from real-world conditions, creating a substantial…

Computer Vision and Pattern Recognition · Computer Science 2025-08-22 Chaojun Ni , Guosheng Zhao , Xiaofeng Wang , Zheng Zhu , Wenkang Qin , Xinze Chen , Guanghong Jia , Guan Huang , Wenjun Mei

Diffusion-based policies have gained growing popularity in solving a wide range of decision-making tasks due to their superior expressiveness and controllable generation during inference. However, effectively training large diffusion…

This paper addresses the challenge of achieving high-quality and fast image generation that aligns with complex human preferences. While recent advancements in diffusion models and distillation have enabled rapid generation, the effective…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Yihong Luo , Tianyang Hu , Weijian Luo , Kenji Kawaguchi , Jing Tang

Reinforcement Learning (RL) has emerged as a central paradigm for advancing Large Language Models (LLMs), where pre-training and RL post-training share the same log-likelihood formulation. In contrast, recent RL approaches for diffusion…

Machine Learning · Computer Science 2025-09-30 Shuchen Xue , Chongjian Ge , Shilong Zhang , Yichen Li , Zhi-Ming Ma

RLHF techniques like DPO can significantly improve the generation quality of text-to-image diffusion models. However, these methods optimize for a single reward that aligns model generation with population-level preferences, neglecting the…

Machine Learning · Computer Science 2025-01-14 Meihua Dang , Anikait Singh , Linqi Zhou , Stefano Ermon , Jiaming Song

Reinforcement learning (RL) has become a standard approach for post-training large language models and, more recently, for improving image generation models, which uses reward functions to enhance generation quality and human preference…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Yunqi Hong , Kuei-Chun Kao , Hengguang Zhou , Cho-Jui Hsieh

A diffusion model, which is formulated to produce an image using thousands of denoising steps, usually suffers from a slow inference speed. Existing acceleration algorithms simplify the sampling by skipping most steps yet exhibit…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Mengfei Xia , Yujun Shen , Changsong Lei , Yu Zhou , Ran Yi , Deli Zhao , Wenping Wang , Yong-Jin Liu

Reward fine-tuning has become a common approach for aligning pretrained diffusion and flow models with human preferences in text-to-image generation. Among reward-gradient-based methods, Adjoint Matching (AM) provides a principled…

Machine Learning · Computer Science 2026-05-19 Jeongwoo Shin , Dongsoo Shin , Yuchen Zhu , Wei Guo , Yongxin Chen , Joonseok Lee , Jaewoong Choi , Jaemoo Choi