Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties
Published in Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
Recommended citation: Keunwoo Yu, Zheyuan Zhang, Fengyuan Hu, Shane Storks, Joyce Chai, "Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties." Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024.
Download Paper