Vq-vla: Improving Vision-language-action Models Via Scaling Vector-quantized Action Tokenizers
Synopsis
[ICCV 2025] VQ-VLA is an innovative vector quantization based action tokenizer built upon the largest-scale action trajectory ...
You Might Also Like
![[Introduction to Computer Vision] 19. Vision-Language-Action (VLA) Models](https://i.ytimg.com/vi/Bnqt-YOkAGI/hq720.jpg?sqp=-oaymwEcCNAFEJQDSFXyq4qpAw4IARUAAIhCGAFwAcABBg==&rs=AOn4CLBf03Q6zd3AM2dC-6w4vJOvUey9sg)
Download Options
Choose a download method below. All links open in new tabs.
| Service | Features | Action |
|---|---|---|
| Ssvid |
MP4 & MP3 • HD Quality • Browser Extension Available
|
Download |
| SaveFrom |
MP4 & MP3 • HD Quality • Browser Extension Available
|
Download |
Security Notice: These are third-party services. We recommend using antivirus software and being cautious of pop-up ads.