TS-LLaVA
by tingyu215
Pythonpushed almost 2 years ago
TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models
AI summary
Video model trainer
This project provides an implementation of a novel approach to training large language models on video data without explicit supervision.
- stars
- 7
- forks
- 0
- watching
- 2