Causal Forcing initializes autoregressive diffusion students from AR teachers to recover flow maps that bidirectional teachers cannot provide, delivering 19%+ gains over Self Forcing on dynamic degree and related metrics.
This interactive world-modeling paradigm further enables embodied intelligence, such as closed-loop control in Vidarc (Feng et al., 2025)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation
Causal Forcing initializes autoregressive diffusion students from AR teachers to recover flow maps that bidirectional teachers cannot provide, delivering 19%+ gains over Self Forcing on dynamic degree and related metrics.