Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Supervising the Visible State: Separating Representation from View Selection in Streaming Video
Yihao Hu, Pan Wang, Yitong Lin +8
An action seen once and the same action seen three times receive the same action-recognition label, so that supervision does not require a model to count. Answers shared across his…
cs.CV2026
ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence
Yihao Hu, Yitong Lin, Pan Wang +8
Training a spatial VLM to answer which side an object lies on does not require it to preserve the metric displacement that determines that answer, while supervision for a distance…