Decoupled surprise-based hierarchical state-space models with top-down inconsistency chunking sustain accurate 250-step open-loop video prediction where prior HSSMs collapse within 10 steps.
Variational predictive routing with nested subjective timescales
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
SUNTA: Hierarchical Video Prediction with Surprise-based Chunking
Decoupled surprise-based hierarchical state-space models with top-down inconsistency chunking sustain accurate 250-step open-loop video prediction where prior HSSMs collapse within 10 steps.