2 papers
cs.CV2026
Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis
Keerthi Kaashyap, Dennis Anthony, Akshay Krishnan +5
This paper examines the role of Novel View Synthesis (NVS) in geometric representation learning. In principle, NVS should reason about 3D scene structure, thereby enabling transfer…
cs.CV2026
MosaicMem: Hybrid Spatial Memory for Controllable Video World Models
Wei Yu, Runjia Qian, Yumeng Li +8
Video diffusion models are moving beyond short, plausible clips toward world simulators that must remain consistent under camera motion, revisits, and intervention. Yet spatial mem…