Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
ACROSSVAM3.0: Resource-Bounded 4D Scene Construction and Adaptive Surface Association
Nan Wu, Hong Yee Hung
Combining video generation, dynamic reconstruction and monocular SLAM requires consistent coordinates, explicit handling of missing outputs and predictable memory use. We present A…
cs.AI2026
AcrossVAM2.0: Conflict-Aware Point Supervision for Parameter-Efficient Video Diffusion Adaptation
Nan Wu, Yee Hung Hong
Explicit point correspondence is attractive for adapting video generators: it describes how visible surfaces move, but can overwrite the appearance prior learned by a large pretrai…