here's where FastVLM comes in



they slap an MLP to project visual tokens from FastViTHD into the LLM's world

the result: way fewer tokens (like 4× less than FastViT, 16× less than ViT‑L/14 at 336‑pixel res). I mean, that's a big dropping in token count and complexity, while
IN3.65%
MLP1.13%
PIXEL0.03%
TOKEN1.3%
post-image
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • 5
  • Repost
  • Share
Comment
0/400
GasFeeLovervip
· 20h ago
That's just how it is, what is there to brag about?
View OriginalReply0
ser_we_are_earlyvip
· 20h ago
It seems FastVLM is really amazing.
View OriginalReply0
BlockchainBardvip
· 20h ago
Impressive! I was shocked by the number of tokens.
View OriginalReply0
WhaleWatchervip
· 21h ago
New things have been made again!
View OriginalReply0
DiamondHandsvip
· 21h ago
Ah, I'm a bit dazed by the blowing...
View OriginalReply0
Trade Crypto Anywhere Anytime
qrCode
Scan to download Gate App
Community
English
  • 简体中文
  • English
  • Tiếng Việt
  • 繁體中文
  • Español
  • Русский
  • Français (Afrique)
  • Português (Portugal)
  • Bahasa Indonesia
  • 日本語
  • بالعربية
  • Українська
  • Português (Brasil)