https://github.com/visresearch/llava-stf
The official implementation of "Learning Compact Vision Tokens for Efficient Large Multimodal Models"
https://github.com/visresearch/llava-stf
efficient-deep-learning efficient-inference large-multimodal-models large-vision-language-models llama llava token-fusion token-merging vision-token-merging
Last synced: 4 months ago
JSON representation
The official implementation of "Learning Compact Vision Tokens for Efficient Large Multimodal Models"
- Host: GitHub
- URL: https://github.com/visresearch/llava-stf
- Owner: visresearch
- License: other
- Created: 2025-05-21T08:11:14.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2025-06-11T02:25:39.000Z (4 months ago)
- Last Synced: 2025-06-20T02:02:13.419Z (4 months ago)
- Topics: efficient-deep-learning, efficient-inference, large-multimodal-models, large-vision-language-models, llama, llava, token-fusion, token-merging, vision-token-merging
- Language: Python
- Homepage:
- Size: 2.62 MB
- Stars: 27
- Watchers: 1
- Forks: 2
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE