Results 11 to 20 of about 488,848 (338)
The Personalization of Conversational Agents in Health Care: Systematic Review
Journal of Medical Internet Research, 2019 BackgroundThe personalization of conversational agents with natural language user interfaces is seeing increasing use in health care applications, shaping the content, structure, or purpose of the dialogue between humans and conversational agents.
Kocaballi, Ahmet Baki +7 more
doaj +2 more sources
LaMP: When Large Language Models Meet Personalization [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 This paper highlights the importance of personalization in large language models and introduces the LaMP benchmark -- a novel benchmark for training and evaluating language models for producing personalized outputs. LaMP offers a comprehensive evaluation
Alireza Salemi +3 more
semanticscholar +1 more source
When large language models meet personalization: perspectives of challenges and opportunities [PDF]
World wide web (Bussum), 2023 The advent of large language models marks a revolutionary breakthrough in artificial intelligence. With the unprecedented scale of training and model parameters, the capability of large language models has been dramatically improved, leading to human ...
Jin Chen +11 more
semanticscholar +1 more source
Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models [PDF]
ACM Transactions on Graphics, 2023 Text-to-image personalization aims to teach a pre-trained diffusion model to reason about novel, user provided concepts, embedding them into new scenes guided by natural language prompts.
Rinon Gal +5 more
semanticscholar +1 more source
HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models [PDF]
Computer Vision and Pattern Recognition, 2023 Personalization has emerged as a prominent aspect within the field of generative AI, enabling the synthesis of individuals in diverse contexts and styles, while retaining high-fidelity to their identities. However, the process of personalization presents
Nataniel Ruiz +8 more
semanticscholar +1 more source
Key-Locked Rank One Editing for Text-to-Image Personalization [PDF]
International Conference on Computer Graphics and Interactive Techniques, 2023 Text-to-image models (T2I) offer a new level of flexibility by allowing users to guide the creative process through natural language. However, personalizing these models to align with user-provided visual concepts remains a challenging problem.
Yoad Tewel +3 more
semanticscholar +1 more source
A Neural Space-Time Representation for Text-to-Image Personalization [PDF]
ACM Transactions on Graphics, 2023 A key aspect of text-to-image personalization methods is the manner in which the target concept is represented within the generative process. This choice greatly affects the visual fidelity, downstream editability, and disk space needed to store the ...
Yuval Alaluf +3 more
semanticscholar +1 more source
PALR: Personalization Aware LLMs for Recommendation [PDF]
arXiv.org, 2023 Large language models (LLMs) have recently received significant attention for their exceptional capabilities. Despite extensive efforts in developing general-purpose LLMs that can be utilized in various natural language processing (NLP) tasks, there has ...
Zheng Chen, Ziyan Jiang
semanticscholar +1 more source
Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generation [PDF]
IEEE International Conference on Computer Vision, 2023 Federated learning (FL) emerges as a decentralized learning framework which trains models from multiple distributed clients without sharing their data to preserve privacy.
Fu-En Yang +2 more
semanticscholar +1 more source
Federated Learning with Partial Model Personalization [PDF]
International Conference on Machine Learning, 2022 We consider two federated learning algorithms for training partially personalized models, where the shared and personal parameters are updated either simultaneously or alternately on the devices.
Krishna Pillutla +5 more
semanticscholar +1 more source