Accelerating Video Diffusion via Training-Free Trajectory Routing
Quick summary
arXiv:2609.30096v1 Announce Type: cross Abstract: Video diffusion is computationally expensive, as it requires executing a large model across many denoising steps. Even with step-distillation, inference remains expensive because every distilled step still requires a costly model evaluation. We present TRACK: TRajectory-Aware Capacity routing via top-K selection, a heterogeneous denoising strategy that switches between compatible large and small models at selected steps, reducing the average cost per denoising evaluation. The switching steps are determined using a calibration process. TRACK fir
Key takeaways
- arXiv:2609.30096v1 Announce Type: cross Abstract: Video diffusion is computationally expensive, as it requires executing a large model across many denoising steps.
- Even with step-distillation, inference remains expensive because every distilled step still requires a costly model evaluation.
- We present TRACK: TRajectory-Aware Capacity routing via top-K selection, a heterogeneous denoising strategy that switches between compatible large and small models at selected steps, reducing the average cost per denoising evaluation.
Why it matters
The value of this work lies as much in how it was tested as in the claim itself. Sample design, baselines, uncertainty and replication help separate a laboratory result from real-world impact.
Member comments