FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression
Paper
•
2412.04317
•
Published
•
1
Bo Tong
Tongbo
AI & ML interests
multimodal learning and efficient training
Recent Activity
liked
a Space
3 days ago
librarian-bots/recommend_similar_papers
published
a dataset
about 1 month ago
Tongbo/test
Organizations
None yet