3 papers
cs.CV2026
SceneForesee: Learning Scene Evolution for Spatiotemporal Reasoning
Chaoyue Li, Shoudong Han, Haoyang Wu +4
Large multimodal models (LMMs) need to understand how entities move and interact as a scene develops. This requires following the same entities over time and relating their observe…
cs.CV2026
ReWorld-Track: A Recursive Event World Model for Language-Guided Multi-Camera Tracking
Haoyang Wu, Shoudong Han, Chaoyue Li +4
Language-guided multi-camera tracking must preserve a target identity across unobserved gaps, where similar candidates and uncertain returns can make early associations unreliable.…
cs.CV2026
4DVLT: Dynamic Scene Understanding with Worldline-Centered Vision-Language Tracking
Chaoyue Li, Boxue Yang, Shengyao Zhou +4
Language-guided dynamic scene understanding requires identifying one physical entity across time, metric 3D space, and multiple viewpoints, a setting not captured by current multim…