CORE: Compact Object-centric REpresentations as a New Paradigm for Token Merging in LVLMs

arXiv — cs.CVWednesday, November 19, 2025 at 5:00:00 AM
  • CORE has been introduced as a new paradigm for visual token compression in Large Vision
  • This development is significant as it establishes a new state
— via World Pulse Now AI Editorial System

Was this article worth reading? Share it

Recommended apps based on your readingExplore all apps

Ready to build your own newsroom?

Subscribe to unlock a personalised feed, podcasts, newsletters, and notifications tailored to the topics you actually care about