paper-with-me

Papers

Aligning Diffusion Models by Optimizing Human Utility

2024-04-06 · Shufan Li, Konstantinos Kallidromitis, Akash Gokul, Yusuke Kato, Kazuki Kozuka

We present Diffusion-KTO, a novel approach for aligning text-to-image diffusion models by formulating the alignment objective as the maximization of expected human utility. Since this objective applies to each generation independently, Diffusion-KTO does not require collecting costly pairwise preference data nor training a complex reward model. Instead, our objective requires simple per-image binary feedback signals, e.g. likes or dislikes, which are abundantly available. After fine-tuning using Diffusion-KTO, text-to-image diffusion models exhibit superior performance compared to existing techniques, including supervised fine-tuning and Diffusion-DPO, both in terms of human judgment and automatic evaluation metrics such as PickScore and ImageReward. Overall, Diffusion-KTO unlocks the potential of leveraging readily available per-image binary signals and broadens the applicability of aligning text-to-image diffusion models with human preferences.

📄 PDF Abstract BibTeX arXiv:2404.04465

Code (2)

jacklishufan/diffusion-kto 공식 구현 pytorch
Shelley-Golan/Boosting-via-Joint-Model pytorch

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Step-level Denoising-time Diffusion Alignment with Multiple Objectives

2026-04-15 · Qi Zhang, Dawei Wang, Shaofeng Zou arxiv

Reinforcement learning (RL) has emerged as a powerful tool for aligning diffusion models with human preferences, typically by optimizing a single reward function under a KL regularization constraint. In practice, however…

Reinforcement Learning

Differentially Private Fine-Tuning of Diffusion Models

2024-06-03 · Yu-Lin Tsai, Yizhe Li, Zekai Chen, Po-Yu Chen 외

The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy r…

Image GenerationMemorizationparameter-efficient fine-tuning

SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset

2024-06-20 · Josef Dai, Tianle Chen, Xuyao Wang, Ziran Yang 외

To mitigate the risk of harmful outputs from large vision models (LVMs), we introduce the SafeSora dataset to promote research on aligning text-to-video generation with human values. This dataset encompasses human prefer…

Safety AlignmentText-to-Video GenerationVideo AlignmentVideo Generation

D3S2: Diffusion-Guided Dataset Distillation for Semantic Segmentation

2026-05-24 · Wenjie Zheng, Haoji Hu, Jiali Lu, Xingze Zou 외 arxiv

Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic sets while preserving training efficacy. However, existing studies mainly focus on image classification, leaving dense prediction tas…

Semantic SegmentationImage Classification

Reinforcement Learning Beyond Expectation

2021-03-29 · Bhaskar Ramasubramanian, Luyao Niu, Andrew Clark, Radha Poovendran

The inputs and preferences of human users are important considerations in situations where these users interact with autonomous cyber or cyber-physical systems. In these scenarios, one is often interested in aligning beh…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)