SUNTA uses surprise-driven chunk boundaries and decoupled training in hierarchical state-space models to sustain accurate video predictions over 250 timesteps where baselines fail after 10.
Learning complex, extended sequences using the principle of history compression.Neural Computation, 4(2), 1992
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SUNTA: Hierarchical Video Prediction with Surprise-based Chunking
SUNTA uses surprise-driven chunk boundaries and decoupled training in hierarchical state-space models to sustain accurate video predictions over 250 timesteps where baselines fail after 10.