CASIM replaces fixed-length text embeddings with token-level cross-attention in text-to-motion models, improving alignment and quality for both diffusion and autoregressive generators.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CASIM: Composite Aware Semantic Injection for Text to Motion Generation
CASIM replaces fixed-length text embeddings with token-level cross-attention in text-to-motion models, improving alignment and quality for both diffusion and autoregressive generators.