SOURCE-LINKED INTELLIGENCE

Rethinking Streaming Video Diffusion Model: Context, Execution, and Training

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

Understanding the design space of streaming video diffusion is essential to exploring its potential for generation quality and computational efficiency. We develop a unified analytical framework that relates model and sampler choices, historical conditioning, execution scheduling, and training strategies. The framework accommodates a broad family of causal context-selection policies and makes their computational dependencies and training-inference alignment explicit. Within this design space, we study three representative policies: clean, same-level, and progressive history. On the full VBench

Read original source ↗ Open in workspace

recordType

paper

region

Global