ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification and KV Cache Compression
Paper
•
2410.08584
•
Published
•
12
•
3
Feng Chen
chenfeng1271
AI & ML interests
Efficient VLM
Recent Activity
updated
a model
3 days ago
chenfeng1271/ZipAR-X-imagenet-256-300-XXL
published
a model
3 days ago
chenfeng1271/ZipAR-X-imagenet-256-300-XXL
updated
a model
17 days ago
chenfeng1271/ZipAR-X-ucf101-256-LP
Organizations
chenfeng1271's activity
commented
a
paper
4 months ago