Skip to content
conftrace_
2025 ICML ICML 2025

Improving LLM Video Understanding with 16 Frames Per Second

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Yixuan Li, Changli Tang, Jimin Zhuang, Yudong Yang, Guangzhi Sun, Wei Li, Zejun Ma, Chao Zhang

Topics

Artificial Intelligence > Core AI > Multimodal Learning Machine Learning > Application Areas > Efficient Computing Artificial Intelligence > Core AI > Large Language Models

Keywords

video understanding semantic information visual token frame rate large language model low-frame-rate inference
Download PDF