paper-with-me

Papers

VisualDeltas: Learning Preferences from Visual Quality Perturbations

2026-03-07 · Hailiang Huang, Yihao Liu, Shengyue Guan, Haoze Li, Sujian Li arxiv

We present VisualDeltas, a lightweight preference-learning framework that extracts supervision from visual quality variations in multimodal data. By leveraging the systematic impact of image quality on visual perception and reasoning, VisualDeltas induces informative preference signals without relying on human annotations or external teachers. The framework supports both label-free and label-based regimes, enabling flexible use of available supervision when present. Across diverse multimodal benchmarks and model scales, VisualDeltas consistently outperforms rejection-sampling fine-tuning and improves generalization, and extends naturally to a range of visual degradations.

📄 PDF Abstract BibTeX arXiv:2603.07272

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Image Quality Assessment: From Human to Machine Preference

2025-03-13 · CVPR 2025 1 · Chunyi Li, Yuan Tian, Xiaoyue Ling, ZiCheng Zhang 외

Image Quality Assessment (IQA) based on human subjective preferences has undergone extensive research in the past decades. However, with the development of communication protocols, the visual data consumption volume of m…

Image Quality Assessment

Visual-Friendly Concept Protection via Selective Adversarial Perturbations

2024-08-16 · Xiaoyue Mi, Fan Tang, Juan Cao, Peng Li 외

Personalized concept generation by tuning diffusion models with a few images raises potential legal and ethical concerns regarding privacy and intellectual property rights. Researchers attempt to prevent malicious person…

Harmonic Adversarial Attack Method

2018-07-18 · Wen Heng, Shuchang Zhou, Tingting Jiang

Adversarial attacks find perturbations that can fool models into misclassifying images. Previous works had successes in generating noisy/edge-rich adversarial perturbations, at the cost of degradation of image quality. S…

Adversarial Attack

Quality Assessment for AI Generated Images with Instruction Tuning

2024-05-12 · Jiarui Wang, Huiyu Duan, Guangtao Zhai, Xiongkuo Min

Artificial Intelligence Generated Content (AIGC) has grown rapidly in recent years, among which AI-based image generation has gained widespread attention due to its efficient and imaginative image creation ability. Howev…

Image GenerationImage Quality Assessment

Personalizing Text-to-Image Generation to Individual Taste

2026-04-08 · Anne-Sofie Maerten, Juliane Verwiebe, Shyamgopal Karthik, Ameya Prabhu 외 arxiv

Modern text-to-image (T2I) models generate high-fidelity visuals but remain indifferent to individual user preferences. While existing reward models optimize for "average" human appeal, they fail to capture the inherent …

Text-to-Image Generation