A distilled video model jointly controls multi-scale upper-body motion latents and two discrete contact states to generate real-time human–object interaction at 25 FPS.
Title resolution pending
1 Pith paper cite this work, alongside 265 external citations. Polarity classification is still indexing.
1
Pith paper citing it
265
external citations · OpenAlex
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Real-Time Human-Centric World Modeling for Upper-Body Human-Object Interaction
A distilled video model jointly controls multi-scale upper-body motion latents and two discrete contact states to generate real-time human–object interaction at 25 FPS.