Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
VASC: Value-Aware Sparse Attention with Cross-Layer Memory for Efficient 3D Reconstruction
Junyi Wu, Fanqing Kong, Leyang Chen +2
Feed-forward 3D vision models such as VGGT have achieved remarkable progress, unifying camera estimation and dense scene reconstruction in a single pass. However, their quadratic g…
cs.CV2026
CAST: Reconstruction-Coupled Acceleration of Interactive World Models
Leyang Chen, Junyi Wu, Fanqing Kong +2
Interactive world models must respond quickly to controls while preserving scene consistency. Existing acceleration methods can miss heterogeneous control responses and spatial tra…