20 results for “Personalization”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Liang Wang, Xinyi Mou, Xiaoyou Liu, Tiannan Wang +2 more
The paper proposes a hierarchical framework, PHF (Practice-Habitus-Field), inspired by Bourdieu's Theory of Practice, to improve LLM personalization by modeling user behaviors at three distinct levels…
This paper investigates how developer attributes influence generated software using AI, finding significant differences in interface design, template content, and code structure based on age and gende…
Thi-Nhung Nguyen, Linhao Luo, Rollin Omari, Junae Kim +2 more
The paper proposes TriAlign, a novel multi-agent reinforcement learning framework that achieves universal truth consistency across social groups in personalized LLMs while maintaining high accuracy an…
This paper investigates the effectiveness of personalization in reading and highlights its limitations.
Zhixin Lin, Jungang Li, Dongliang Xu, Shidong Pan +4 more
The paper proposes Trajectory Induced Preference Optimization (TIPO) to improve mobile GUI agent personalization by explicitly modeling and optimizing for privacy-related behavioral differences in exe…
Zhixu Li, Keqian Tang, Litian Gong, Jingyu Yao +6 more
This paper introduces LIBERO-PeRM, a benchmark for preference learning in embodied agents, and evaluates current policies' ability to learn and generalize preferences.
The paper proposes a method called Context-Continuous Preference Learning (CCPL) to personalize exoskeleton assistance across different operating conditions with limited user feedback.
Hanwen Cui, Yuting Mei, Yuhang Fu, Dingyi Yang +1 more
The paper introduces STORYLENSWRITER, a novel framework that significantly improves personalized story rewriting by incorporating context-aware narrative enrichment, outperforming style-only adaptatio…
Chuanzhi Xu, Ziyuan Tao, Jean Julien KNell, Yanrong Chen +4 more
This paper introduces FedPAIE, a federated learning framework for personalized image enhancement without centralizing raw photos or ratings.
Hengji Zhou, Ye Liu, Yufeng Liu, Si Wu +2 more
This paper proposes TailorMind, a system that generates personalized multimodal content without relying on existing user-generated content.
A system was designed to provide AI-generated response suggestions for social media content creators to maintain their media personas and reduce fatigue.
This study explores why and how users customize social AI, identifying motivations and contributions to a closer relationship.
The study found that while contextualizing AI responses reduces their persuasive power, combining this technique with conversational warmth restores persuasiveness, suggesting that user deference to A…
Lingyang Zeng, Guangze Chen, Kaichen Yu, Zhicheng Pan +8 more
This paper proposes Setoka, a benchmark for evaluating memory-augmented personalized agents with hierarchical user understanding from heterogeneous data.
Equilibrated Diffusion introduces a frequency-aware approach to image customization, disentangling style and subject content embeddings to achieve superior subject fidelity and text adherence.
Jingyuan Zheng, Xin Zhang, Yang Gu, Dongjing Wang +5 more
This paper evaluates the effectiveness of per-user modality weighting in multimodal recommenders and finds that a single global modality weight delivers most of the content gain.