AINeutralarXiv – CS AI · 7h ago6/10
🧠
Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models
Researchers propose Reroute, a training-free method that improves vision-language model efficiency by recoverable token routing instead of permanent token removal. The approach dynamically reroutes less important visual tokens through decoder layers rather than discarding them, improving performance on grounding tasks while maintaining computational efficiency.