All Papers

0 / 0 papers shown

Title

Few-Shot VQA with Frozen LLMs: A Tale of Two Approaches

Few-Shot VQA with Frozen LLMs: A Tale of Two Approaches

17 March 2024

ArXiv (abs)PDF HTML

Papers citing "Few-Shot VQA with Frozen LLMs: A Tale of Two Approaches"

3 / 3 papers shown

Title
FEALLM: Advancing Facial Emotion Analysis in Multimodal Large Language Models with Emotional Synergy and Reasoning Zhuozhao Hu Kaishen Yuan Xin Liu Zitong Yu Yuan Zong Jingang Shi Huanjing Yue Jingyu Yang 167 7 0 19 May 2025
VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video UnderstandingComputer Vision and Pattern Recognition (CVPR), 2024 Kangsan Kim G. Park Youngwan Lee Woongyeong Yeo Sung Ju Hwang 285 10 0 03 Dec 2024
Billion-scale similarity search with GPUsIEEE Transactions on Big Data (TBD), 2017 Jeff Johnson Matthijs Douze Edouard Grave 797 4,389 0 28 Feb 2017