English
Related papers

Related papers: Human Preference-Aligned Concept Customization Ben…

200 papers

Benchmarking autonomous driving planners to align with human judgment remains a critical challenge, as state-of-the-art metrics like the Extended Predictive Driver Model Score (EPDMS) lack context awareness in nuanced scenarios. To address…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Jingyu Song , Zhenxin Li , Shiyi Lan , Xinglong Sun , Nadine Chang , Maying Shen , Joshua Chen , Katherine A. Skinner , Jose M. Alvarez

A variety of text-guided image editing models have been proposed recently. However, there is no widely-accepted standard evaluation method mainly due to the subjective nature of the task, letting researchers rely on manual user study. To…

Computer Vision and Pattern Recognition · Computer Science 2025-05-02 Suho Ryu , Kihyun Kim , Eugene Baek , Dongsoo Shin , Joonseok Lee

Reward models (RMs) are essential for aligning large language models (LLMs) with human preferences to improve interaction quality. However, the real world is pluralistic, which leads to diversified human preferences with respect to…

Computation and Language · Computer Science 2023-09-18 Pengyu Cheng , Jiawen Xie , Ke Bai , Yong Dai , Nan Du

Understanding the quality of a performance evaluation metric is crucial for ensuring that model outputs align with human preferences. However, it remains unclear how well each metric captures the diverse aspects of these preferences, as…

Computation and Language · Computer Science 2025-03-04 Genta Indra Winata , David Anugraha , Lucky Susanto , Garry Kuwanto , Derry Tanti Wijaya

Iterative prompt refinement is central to reproducing target images with text to image generative models. Previous studies have incorporated image similarity metrics (ISMs) as additional feedback to human users. Existing ISMs such as LPIPS…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Khoi Trinh , Jay Rothenberger , Scott Seidenberger , Dimitrios Diochnos , Anindya Maiti

Despite recent advances in text-to-3D generative methods, there is a notable absence of reliable evaluation metrics. Existing metrics usually focus on a single criterion each, such as how well the asset aligned with the input text. These…

Computer Vision and Pattern Recognition · Computer Science 2024-01-11 Tong Wu , Guandao Yang , Zhibing Li , Kai Zhang , Ziwei Liu , Leonidas Guibas , Dahua Lin , Gordon Wetzstein

Models of human feedback for AI alignment, such as those underpinning Direct Preference Optimization (DPO), often bake in a singular, static set of preferences, limiting adaptability. This paper challenges the assumption of monolithic…

Computation and Language · Computer Science 2025-06-16 Víctor Gallego

Multimodal Large Language Models (MLLMs) have demonstrated significant advances in visual understanding tasks. However, their capacity to comprehend human-centric scenes has rarely been explored, primarily due to the absence of…

Computer Vision and Pattern Recognition · Computer Science 2025-10-16 Yuansen Liu , Haiming Tang , Jinlong Peng , Jiangning Zhang , Xiaozhong Ji , Qingdong He , Wenbin Wu , Donghao Luo , Zhenye Gan , Junwei Zhu , Yunhang Shen , Chaoyou Fu , Chengjie Wang , Xiaobin Hu , Shuicheng Yan

Generative Artificial Intelligence (AI) has enabled the development of sophisticated models that are capable of producing high-caliber text, images, and other outputs through the utilization of large pre-trained models. Nevertheless,…

Computation and Language · Computer Science 2023-02-14 Jinlan Fu , See-Kiong Ng , Zhengbao Jiang , Pengfei Liu

Personalized image generation has emerged as a promising direction in multimodal content creation. It aims to synthesize images tailored to individual style preferences (e.g., color schemes, character appearances, layout) and semantic…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Yiyan Xu , Wuqiang Zheng , Wenjie Wang , Fengbin Zhu , Xinting Hu , Yang Zhang , Fuli Feng , Tat-Seng Chua

The evaluation of large language models faces significant challenges. Technical benchmarks often lack real-world relevance, while existing human preference evaluations suffer from unrepresentative sampling, superficial assessment depth, and…

Computation and Language · Computer Science 2026-03-06 Nora Petrova , Andrew Gordon , Enzo Blindow

Layout generation plays a crucial role in enhancing both user experience and design efficiency. However, current approaches suffer from task-specific generation capabilities and perceptually misaligned evaluation metrics, leading to limited…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Shuo Lu , Yanyin Chen , Wei Feng , Jiahao Fan , Fengheng Li , Zheng Zhang , Jingjing Lv , Junjie Shen , Ching Law , Jian Liang

Human preference alignment can greatly enhance Multimodal Large Language Models (MLLMs), but collecting high-quality preference data is costly. A promising solution is the self-evolution strategy, where models are iteratively trained on…

Machine Learning · Computer Science 2024-12-23 Wentao Tan , Qiong Cao , Yibing Zhan , Chao Xue , Changxing Ding

Recent research has increasingly focused on evaluating large language models' (LLMs) alignment with diverse human values and preferences, particularly for open-ended tasks like story generation. Traditional evaluation metrics rely heavily…

Computation and Language · Computer Science 2024-10-07 Danqing Wang , Kevin Yang , Hanlin Zhu , Xiaomeng Yang , Andrew Cohen , Lei Li , Yuandong Tian

Driven by the remarkable progress in diffusion models, text-to-image generation has made significant strides, creating a pressing demand for automatic quality evaluation of generated images. Current state-of-the-art automatic evaluation…

Computation and Language · Computer Science 2024-11-26 Rong-Cheng Tu , Zi-Ao Ma , Tian Lan , Yuehao Zhao , Heyan Huang , Xian-Ling Mao

Modern alignment pipelines are increasingly replacing expensive human preference labels with evaluations from large language models (LLM-as-Judge). However, AI labels can be systematically biased compared to high-quality human feedback…

Machine Learning · Statistics 2026-02-10 Xintao Xia , Zhiqiu Xia , Linjun Zhang , Zhanrui Cai

Human preferences are widely used to align large language models (LLMs) through methods such as reinforcement learning from human feedback (RLHF). However, the current user interfaces require annotators to compare text paragraphs, which is…

Human-Computer Interaction · Computer Science 2025-07-28 Danqing Shi , Furui Cheng , Tino Weinkauf , Antti Oulasvirta , Mennatallah El-Assady

Search-augmented large language models (LLMs) have advanced information-seeking tasks by integrating retrieval into generation, reducing users' cognitive burden compared to traditional search systems. Yet they remain insufficient for fully…

Computation and Language · Computer Science 2026-05-27 Hyunseo Kim , Sangam Lee , Kwangwook Seo , Dongha Lee

As language models (LMs) become more capable, it is increasingly important to align them with human preferences. However, the dominant paradigm for training Preference Models (PMs) for that purpose suffers from fundamental limitations, such…

Computation and Language · Computer Science 2024-03-18 Dongyoung Go , Tomasz Korbak , Germán Kruszewski , Jos Rozen , Marc Dymetman

Continuous prompts have become widely adopted for augmenting performance across a wide range of natural language tasks. However, the underlying mechanism of this enhancement remains obscure. Previous studies rely on individual words for…

Computation and Language · Computer Science 2024-12-06 Qian Chen , Dongyang Li , Xiaofeng He