3 papers
cs.CV2026
OmniX: Any-view and Any-time 4D Reconstruction via Feed-forward Trajectory Fields
Yanqin Jiang, Tengfei Wang, Zhengwei Wang +6
Previous feed-forward 4D reconstruction methods either predict per-frame static point clouds, ignoring foreground motion, or estimate point cloud trajectories while being limited t…
cs.CV2026
OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models
Yiwei Zhang, Xuesong Chen, Jin Gao +5
Vision-Language Models(VLMs) excel at autoregressive text generation, yet end-to-end autonomous driving requires multi-task learning with structured outputs and heterogeneous decod…
cs.CV2026
MMPhysVideo: Physically Plausible Video Generation Through Joint RGB-Perception Modeling
Shubo Lin, Xuanyang Zhang, Wei Cheng +3
Despite advancements in generating visually stunning content, video diffusion models (VDMs) often yield physically inconsistent results due to pixel-only reconstruction. To address…