DraftAttention2 is presented, a training-free framework that uses the low-resolution draft attention map to jointly select attention blocks and assign their numerical precision, and achieves a superior quality-efficiency trade-off over existing efficient video generation methods.
Rui Ding, Haopeng Li, Wei-Ze Ma et al.· 0 citations
VeriPhy, an auditable physical-verification system in which a text-only planner compiles the prompt into typed physical obligations and a statically validated execution plan before any frame is observed, is presented.
Wenzhuo Xu, Yu-Chen Zhu, Chongjian Ge et al.· 0 citations
ADOPD 2026 is presented, a reasoning-oriented extension of ADOPD that turns page decomposition into spatially grounded document understanding and provides a task framework that moves document understanding beyond localization toward anchor-grounded document intelligence.
Sichen Zhu, Yuchen Zhu, Wenzhuo Xu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.