A one-stage Transformer with placeholder tokens generates continuous 2D pose sequences from a single image and text, avoiding autoregressive error accumulation.
The pitfalls of next-token prediction, 2024
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Towards Consistent Long-Term Pose Generation
A one-stage Transformer with placeholder tokens generates continuous 2D pose sequences from a single image and text, avoiding autoregressive error accumulation.