A²RD uses an agentic autoregressive diffusion model with multimodal memory, adaptive segment generation, and hierarchical self-improvement to outperform baselines by up to 30% in consistency on long video benchmarks including a new LVBench-C.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
A$^2$RD: Agentic Autoregressive Diffusion for Long Video Consistency
A²RD uses an agentic autoregressive diffusion model with multimodal memory, adaptive segment generation, and hierarchical self-improvement to outperform baselines by up to 30% in consistency on long video benchmarks including a new LVBench-C.