تقرير
Digital Avatars: Framework Development and Their Evaluation
| العنوان: | Digital Avatars: Framework Development and Their Evaluation |
|---|---|
| المؤلفون: | Rupprecht, Timothy, Chang, Sung-En, Wu, Yushu, Lu, Lei, Nan, Enfu, Li, Chih-hsiang, Lai, Caiyue, Li, Zhimin, Hu, Zhijun, He, Yumei, Kaeli, David, Wang, Yanzhi |
| المصدر: | 2024 Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence Demo Track. Pages 8780-8783 |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Artificial Intelligence, 68, D.2.2, C.3 |
| الوصف: | We present a novel prompting strategy for artificial intelligence driven digital avatars. To better quantify how our prompting strategy affects anthropomorphic features like humor, authenticity, and favorability we present Crowd Vote - an adaptation of Crowd Score that allows for judges to elect a large language model (LLM) candidate over competitors answering the same or similar prompts. To visualize the responses of our LLM, and the effectiveness of our prompting strategy we propose an end-to-end framework for creating high-fidelity artificial intelligence (AI) driven digital avatars. This pipeline effectively captures an individual's essence for interaction and our streaming algorithm delivers a high-quality digital avatar with real-time audio-video streaming from server to mobile device. Both our visualization tool, and our Crowd Vote metrics demonstrate our AI driven digital avatars have state-of-the-art humor, authenticity, and favorability outperforming all competitors and baselines. In the case of our Donald Trump and Joe Biden avatars, their authenticity and favorability are rated higher than even their real-world equivalents. Comment: This work was presented during the IJCAI 2024 conference proceedings for demonstrations |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.24963/ijcai.2024/1031 |
| URL الوصول: | http://arxiv.org/abs/2408.04068 |
| رقم الأكسشن: | edsarx.2408.04068 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.24963/ijcai.2024/1031 |
|---|