Long-horizon Video Generation with Slot Memory Addressed By Region Tokens
Memory for long-horizon video generation must satisfy two competing requirements: it must remain bounded so generation can continue indefinitely, while still recovering what was observed at a place when the camera returns, regardless of how long ago it was seen.
By Eren Cetin, Julius Erbach, Vukasin Bozic, Hyojun Go, Zixiang Zhao, Nikolai Kalischek, Federico Tombari, Konrad Schindler, Dominik NarnhoferarXiv - cs.CV (CV)
Read the full story
Originally published by arXiv - cs.CV (CV) on Oct 15, 2026.
Comments
Sign in to join the discussion.