SIMS couples retrieval-augmented LLM scripts with a text-conditioned, physics-based control policy to generate stylized human-scene interactions.
C· ase: Learning conditional adversar- ial skill embeddings for physics-based characters
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation
SIMS couples retrieval-augmented LLM scripts with a text-conditioned, physics-based control policy to generate stylized human-scene interactions.