English
Related papers

Related papers: Direct Preference Optimization-Enhanced Multi-Guid…

200 papers

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

Direct Preference Optimization (DPO) has been successfully used to align large language models (LLMs) according to human preferences, and more recently it has also been applied to improving the quality of text-to-image diffusion models.…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Shivanshu Shekhar , Shreyas Singh , Tong Zhang

Recent studies have demonstrated the effectiveness of directly aligning diffusion models with human preferences using differentiable reward. However, they exhibit two primary challenges: (1) they rely on multistep denoising with gradient…

Artificial Intelligence · Computer Science 2025-09-12 Xiangwei Shen , Zhimin Li , Zhantao Yang , Shiyi Zhang , Yingfang Zhang , Donghao Li , Chunyu Wang , Qinglin Lu , Yansong Tang

Aligning text-to-image (T2I) diffusion models with Direct Preference Optimization (DPO) has shown notable improvements in generation quality. However, applying DPO to T2I faces two challenges: the sensitivity of DPO to preference pairs and…

Computer Vision and Pattern Recognition · Computer Science 2025-05-19 Renjie Chen , Wenfeng Lin , Yichen Zhang , Jiangchuan Wei , Boyuan Liu , Chao Feng , Jiao Ran , Mingyu Guo

Direct Preference Optimization (DPO) has emerged as a de-facto approach for aligning language models with human preferences. Recent work has shown DPO's effectiveness relies on training data quality. In particular, clear quality differences…

Machine Learning · Computer Science 2025-01-28 Nirav Diwan , Tolga Ergen , Dongsub Shim , Honglak Lee

Diffusion models have recently gained prominence in offline reinforcement learning due to their ability to effectively learn high-performing, generalizable policies from static datasets. Diffusion-based planners facilitate long-horizon…

Machine Learning · Computer Science 2025-10-27 Donghyeon Ki , JunHyeok Oh , Seong-Woong Shim , Byung-Jun Lee

Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or classifier pretraining. That is why guidance was harnessed from self-supervised learning backbones, like…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Vincent Tao Hu , Yunlu Chen , Mathilde Caron , Yuki M. Asano , Cees G. M. Snoek , Bjorn Ommer

Recently, the diffusion model has emerged as a powerful generative technique for robotic policy learning, capable of modeling multi-mode action distributions. Leveraging its capability for end-to-end autonomous driving is a promising…

Computer Vision and Pattern Recognition · Computer Science 2025-04-11 Bencheng Liao , Shaoyu Chen , Haoran Yin , Bo Jiang , Cheng Wang , Sixu Yan , Xinbang Zhang , Xiangyu Li , Ying Zhang , Qian Zhang , Xinggang Wang

Accurate prediction of human or vehicle trajectories with good diversity that captures their stochastic nature is an essential task for many applications. However, many trajectory prediction models produce unreasonable trajectory samples…

Computer Vision and Pattern Recognition · Computer Science 2025-02-10 Qingze , Liu , Danrui Li , Samuel S. Sohn , Sejong Yoon , Mubbasir Kapadia , Vladimir Pavlovic

End-to-end autonomous driving has substantially progressed by directly predicting future trajectories from raw perception inputs, which bypasses traditional modular pipelines. However, mainstream methods trained via imitation learning…

Robotics · Computer Science 2025-09-23 Shuyao Shang , Yuntao Chen , Yuqi Wang , Yingyan Li , Zhaoxiang Zhang

Preference-based reinforcement learning (RL) is a key paradigm for aligning policies with human judgments, yet its theoretical behavior in distributed settings where preference data are fragmented across heterogeneous users remains poorly…

Machine Learning · Computer Science 2026-05-21 Zhanhong Jiang

Human image generation is a key focus in image synthesis due to its broad applications, but even slight inaccuracies in anatomy, pose, or details can compromise realism. To address these challenges, we explore Direct Preference Optimization…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Sanghyeon Na , Yonggyu Kim , Hyunjoon Lee

Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback (RLHF) for large language models (LLMs) by directly optimizing human preferences without an explicit reward model. We find that during DPO training,…

Computation and Language · Computer Science 2026-01-01 Junshu Pan , Wei Shen , Shulin Huang , Qiji Zhou , Yue Zhang

Previous text-to-image diffusion models typically employ supervised fine-tuning (SFT) to enhance pre-trained base models. However, this approach primarily minimizes the loss of mean squared error (MSE) at the pixel level, neglecting the…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Liang Peng , Boxi Wu , Haoran Cheng , Yibo Zhao , Xiaofei He

Traditional preference tuning methods for LLMs/Visual Generative Models often rely solely on reward model labeling, which can be opaque, offer limited insights into the rationale behind preferences, and are prone to issues such as reward…

Machine Learning · Computer Science 2026-01-13 Hanyang Zhao , Haoxian Chen , Yucheng Guo , Genta Indra Winata , Tingting Ou , Ziyu Huang , David D. Yao , Wenpin Tang

Developing efficient multi-objective optimization methods to compute the Pareto set of optimal compromises between conflicting objectives remains a key challenge, especially for large-scale and expensive problems. To bridge this gap, we…

Machine Learning · Computer Science 2026-02-05 Sedjro Salomon Hotegni , Sebastian Peitz

Text-to-image (T2I) diffusion models have made remarkable strides in generating and editing high-fidelity images from text. Yet, these models remain fundamentally generic, failing to adapt to the nuanced aesthetic preferences of individual…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Connor Dunlop , Matthew Zheng , Kavana Venkatesh , Pinar Yanardag

Safe and effective motion planning is crucial for autonomous robots. Diffusion models excel at capturing complex agent interactions, a fundamental aspect of decision-making in dynamic environments. Recent studies have successfully applied…

Robotics · Computer Science 2025-07-18 Giwon Lee , Daehee Park , Jaewoo Jeong , Kuk-Jin Yoon

Aligning text-to-image (T2I) diffusion models with preference optimization is valuable for human-annotated datasets, but the heavy cost of manual data collection limits scalability. Using reward models offers an alternative, however,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Kyungmin Lee , Xiaohang Li , Qifei Wang , Junfeng He , Junjie Ke , Ming-Hsuan Yang , Irfan Essa , Jinwoo Shin , Feng Yang , Yinxiao Li

Direct Preference Optimization (DPO) has recently been applied as a post-training technique for text-to-video diffusion models. To obtain training data, annotators are asked to provide preferences between two videos generated from…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Ziyi Wu , Anil Kag , Ivan Skorokhodov , Willi Menapace , Ashkan Mirzaei , Igor Gilitschenski , Sergey Tulyakov , Aliaksandr Siarohin