AHCI RESEARCH GROUP
Publications
Papers published in international journals,
proceedings of conferences, workshops and books.
OUR RESEARCH
Scientific Publications
How to
Here you can find the complete list of our publications.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
2025
Guo, H.; Liu, Z.; Tang, C.; Zhang, X.
An Interactive Framework for Personalized Navigation Based on Metacosmic Cultural Tourism and Large Model Fine-Tuning Journal Article
In: IEEE Access, vol. 13, pp. 81450–81461, 2025, ISSN: 21693536 (ISSN).
Abstract | Links | BibTeX | Tags: Cultural informations, Digital Cultural Heritage, Digital cultural heritages, Digital guide, Fine tuning, fine-tuning, Historical monuments, Language Model, Large language model, Leisure, Metacosmic cultural tourism, Multimodal Interaction, Tourism, Virtual tour
@article{guo_interactive_2025,
title = {An Interactive Framework for Personalized Navigation Based on Metacosmic Cultural Tourism and Large Model Fine-Tuning},
author = {H. Guo and Z. Liu and C. Tang and X. Zhang},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105004059236&doi=10.1109%2fACCESS.2025.3565359&partnerID=40&md5=45d328831c5795fa31e7e033299912b5},
doi = {10.1109/ACCESS.2025.3565359},
issn = {21693536 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {IEEE Access},
volume = {13},
pages = {81450–81461},
abstract = {With the wide application of large language models (LLMs) and the rapid growth of metaverse tourism demand, the digital tour and personalized interaction of historical sites have become the key to improving users’ digital travel experience. Creating an environment where users can access rich cultural information and enjoy personalized, immersive experiences is a crucial issue in the field of digital cultural travel. To this end, we propose a tourism information multimodal generation personalized question-answering interactive framework TIGMI (Tourism Information Generation and Multimodal Interaction) based on LLM fine-tuning, which aims to provide a richer and more in-depth experience for virtual tours of historical monuments. Taking Qutan Temple as an example, the framework combines LLM, retrieval augmented generation (RAG), and auto-prompting engineering techniques to retrieve accurate information related to the historical monument from external knowledge bases and seamlessly integrates it into the generated content. This integration mechanism ensures the accuracy and relevance of the generated answers. Through TIGMI’s LLM-driven command interaction mechanism in the 3D digital scene of Qutan Temple, users are able to interact with the building and scene environment in a personalized and real-time manner, successfully integrating historical and cultural information with modern digital technology. This integration significantly enhances the naturalness of interaction and personalizes the user experience, thereby improving user immersion and information acquisition efficiency. Evaluation results show that TIGMI excels in question-answering and multimodal interactions, significantly enhancing the depth and breadth of services provided by the personalized virtual tour. We conclude by addressing the limitations of TIGMI and briefly discuss how future research will focus on further improving the accuracy and user satisfaction of the generated content to adapt to the dynamically changing tourism environment. © 2013 IEEE.},
keywords = {Cultural informations, Digital Cultural Heritage, Digital cultural heritages, Digital guide, Fine tuning, fine-tuning, Historical monuments, Language Model, Large language model, Leisure, Metacosmic cultural tourism, Multimodal Interaction, Tourism, Virtual tour},
pubstate = {published},
tppubtype = {article}
}
With the wide application of large language models (LLMs) and the rapid growth of metaverse tourism demand, the digital tour and personalized interaction of historical sites have become the key to improving users’ digital travel experience. Creating an environment where users can access rich cultural information and enjoy personalized, immersive experiences is a crucial issue in the field of digital cultural travel. To this end, we propose a tourism information multimodal generation personalized question-answering interactive framework TIGMI (Tourism Information Generation and Multimodal Interaction) based on LLM fine-tuning, which aims to provide a richer and more in-depth experience for virtual tours of historical monuments. Taking Qutan Temple as an example, the framework combines LLM, retrieval augmented generation (RAG), and auto-prompting engineering techniques to retrieve accurate information related to the historical monument from external knowledge bases and seamlessly integrates it into the generated content. This integration mechanism ensures the accuracy and relevance of the generated answers. Through TIGMI’s LLM-driven command interaction mechanism in the 3D digital scene of Qutan Temple, users are able to interact with the building and scene environment in a personalized and real-time manner, successfully integrating historical and cultural information with modern digital technology. This integration significantly enhances the naturalness of interaction and personalizes the user experience, thereby improving user immersion and information acquisition efficiency. Evaluation results show that TIGMI excels in question-answering and multimodal interactions, significantly enhancing the depth and breadth of services provided by the personalized virtual tour. We conclude by addressing the limitations of TIGMI and briefly discuss how future research will focus on further improving the accuracy and user satisfaction of the generated content to adapt to the dynamically changing tourism environment. © 2013 IEEE.
2024
Liew, Z. Q.; Xu, M.; Lim, W. Y. Bryan; Niyato, D.; Kim, D. I.
AI-Generated Bidding for Immersive AIGC Services in Mobile Edge-Empowered Metaverse Proceedings Article
In: Int. Conf. Inf. Networking, pp. 305–309, IEEE Computer Society, 2024, ISBN: 19767684 (ISSN); 979-835033094-6 (ISBN).
Abstract | Links | BibTeX | Tags: Artificial intelligence generated bid, Artificial intelligence generated content, Bidding mechanism, Bidding models, Budget constraint, Budget control, Budget-constraint bidding, Constrained optimization, Content services, Immersive, Learning systems, Metaverses, Mobile edge computing, Reinforcement Learning, Semantics, Virtual tour
@inproceedings{liew_ai-generated_2024,
title = {AI-Generated Bidding for Immersive AIGC Services in Mobile Edge-Empowered Metaverse},
author = {Z. Q. Liew and M. Xu and W. Y. Bryan Lim and D. Niyato and D. I. Kim},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85198324990&doi=10.1109%2fICOIN59985.2024.10572159&partnerID=40&md5=271f5c45e8e95f01b42acaee89599bd5},
doi = {10.1109/ICOIN59985.2024.10572159},
isbn = {19767684 (ISSN); 979-835033094-6 (ISBN)},
year = {2024},
date = {2024-01-01},
booktitle = {Int. Conf. Inf. Networking},
pages = {305–309},
publisher = {IEEE Computer Society},
abstract = {Recent advancements in Artificial Intelligence Generated Content (AIGC) provide personalized and immersive content generation services for applications such as interactive advertisements, virtual tours, and metaverse. With the use of mobile edge computing (MEC), buyers can bid for the AIGC service to enhance their user experience in real-time. However, designing strategies to optimize the quality of the services won can be challenging for budget-constrained buyers. The performance of classical bidding mechanisms is limited by the fixed rules in the strategies. To this end, we propose AI-generated bidding (AIGB) to optimize the bidding strategies for AIGC. AIGB model uses reinforcement learning model to generate bids for the services by learning from the historical data and environment states such as remaining budget, budget consumption rate, and quality of the won services. To obtain quality AIGC service, we propose a semantic aware reward function for the AIGB model. The proposed model is tested with a real-world dataset and experiments show that our model outperforms the classical bidding mechanism in terms of the number of services won and the similarity score. © 2024 IEEE.},
keywords = {Artificial intelligence generated bid, Artificial intelligence generated content, Bidding mechanism, Bidding models, Budget constraint, Budget control, Budget-constraint bidding, Constrained optimization, Content services, Immersive, Learning systems, Metaverses, Mobile edge computing, Reinforcement Learning, Semantics, Virtual tour},
pubstate = {published},
tppubtype = {inproceedings}
}
Recent advancements in Artificial Intelligence Generated Content (AIGC) provide personalized and immersive content generation services for applications such as interactive advertisements, virtual tours, and metaverse. With the use of mobile edge computing (MEC), buyers can bid for the AIGC service to enhance their user experience in real-time. However, designing strategies to optimize the quality of the services won can be challenging for budget-constrained buyers. The performance of classical bidding mechanisms is limited by the fixed rules in the strategies. To this end, we propose AI-generated bidding (AIGB) to optimize the bidding strategies for AIGC. AIGB model uses reinforcement learning model to generate bids for the services by learning from the historical data and environment states such as remaining budget, budget consumption rate, and quality of the won services. To obtain quality AIGC service, we propose a semantic aware reward function for the AIGB model. The proposed model is tested with a real-world dataset and experiments show that our model outperforms the classical bidding mechanism in terms of the number of services won and the similarity score. © 2024 IEEE.
Vasic, I.; Fill, H. -G.; Quattrini, R.; Pierdicca, R.
LLM-Aided Museum Guide: Personalized Tours Based on User Preferences Proceedings Article
In: L.T., De Paolis; P., Arpaia; M., Sacco (Ed.): Lect. Notes Comput. Sci., pp. 249–262, Springer Science and Business Media Deutschland GmbH, 2024, ISBN: 03029743 (ISSN); 978-303171709-3 (ISBN).
Abstract | Links | BibTeX | Tags: Artificial intelligence techniques, Automated process, Cultural heritages, Extended reality, Language Model, Large language model, large language models, Modeling languages, Museum guide, User's preferences, Virtual environments, Virtual museum, Virtual museums, Virtual tour
@inproceedings{vasic_llm-aided_2024,
title = {LLM-Aided Museum Guide: Personalized Tours Based on User Preferences},
author = {I. Vasic and H. -G. Fill and R. Quattrini and R. Pierdicca},
editor = {De Paolis L.T. and Arpaia P. and Sacco M.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85205127699&doi=10.1007%2f978-3-031-71710-9_18&partnerID=40&md5=fba73e38a432e0749b8e79197ef85310},
doi = {10.1007/978-3-031-71710-9_18},
isbn = {03029743 (ISSN); 978-303171709-3 (ISBN)},
year = {2024},
date = {2024-01-01},
booktitle = {Lect. Notes Comput. Sci.},
volume = {15029 LNCS},
pages = {249–262},
publisher = {Springer Science and Business Media Deutschland GmbH},
abstract = {The quick development of generative artificial intelligence (GenAI) techniques is a promising step toward automated processes in the field of cultural heritage (CH). The recent rise of powerful Large Language Models (LLMs) like ChatGPT has made them a commonly utilized tool for a wide range of tasks across various fields. In this paper, we introduce LLMs as a guide in the three-dimensional (3D) panoramic virtual tour of the Civic Art Gallery of Ascoli to enable visitors to express their interest and show them the requested content. The input to our algorithm is a user request in natural language. The processing tasks are performed with the OpenAI’s Generative Pre-trained Transformer (GPT) 4o model. Requests are handled through the OpenAI’s API. We demonstrate all the functionalities within a developed local web-based application. This novel approach is capable of solving the problem of generic guided tours in the museum and offers a solution for the more automatized and personalized ones. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.},
keywords = {Artificial intelligence techniques, Automated process, Cultural heritages, Extended reality, Language Model, Large language model, large language models, Modeling languages, Museum guide, User's preferences, Virtual environments, Virtual museum, Virtual museums, Virtual tour},
pubstate = {published},
tppubtype = {inproceedings}
}
The quick development of generative artificial intelligence (GenAI) techniques is a promising step toward automated processes in the field of cultural heritage (CH). The recent rise of powerful Large Language Models (LLMs) like ChatGPT has made them a commonly utilized tool for a wide range of tasks across various fields. In this paper, we introduce LLMs as a guide in the three-dimensional (3D) panoramic virtual tour of the Civic Art Gallery of Ascoli to enable visitors to express their interest and show them the requested content. The input to our algorithm is a user request in natural language. The processing tasks are performed with the OpenAI’s Generative Pre-trained Transformer (GPT) 4o model. Requests are handled through the OpenAI’s API. We demonstrate all the functionalities within a developed local web-based application. This novel approach is capable of solving the problem of generic guided tours in the museum and offers a solution for the more automatized and personalized ones. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.