cs.CVNov 17, 2026

BATMoS: Budget-Aware Guidance Allocation for Efficient Video Diffusion

Authors: Zhixu Du, Kuo Yang, Jingwei Sun, Hai "Helen" Li, Yiran Chen

Organizations: Duke University · University of Florida

Abstract

The effectiveness of a video diffusion model's inference budget depends on where computation is spent along the denoising trajectory. Across eight equal-budget inference configurations, VBench total scores span 4.80 points, highlighting the importance of explicit allocation design. Our key insight is that guidance evaluations are not equally valuable across diffusion time: retaining the sampling updates while selectively reusing guidance can preserve generation quality with fewer denoiser evaluations. We introduce BATMoS (Budget Aware Temporal Mixture of Strategies), which routes between fresh classifier-free guidance and cached guidance using a single pretrained denoiser. A magnitude-based temporal rule assigns guidance reuse to low-magnitude blocks and reserves fresh guidance for the remaining blocks, with a single integer controlling the computation budget. The resulting schedule requires no additional router training or per-budget threshold search. Evaluated on CogVideoX-2B with 4,720 videos per configuration across all sixteen official VBench dimensions, BATMoS achieves the highest total score among the eight allocation policies and comes within 0.10 points of full classifier-free guidance using 20% fewer branch evaluations. BATMoS also composes with feature reuse, reducing computation from 80 to 62 effective branch evaluations with a 0.11-point decrease in total score. These findings make temporal guidance allocation a practical mechanism for extracting more generation quality from a fixed inference budget.

Figures & tables

Explore similar work

CardsList
  1. LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion

    Mar 15, 2026Zengqun Zhao, Ziquan Liu, Yu Cao +5Video Diffusion ModelsInference-Time Scaling

  2. Heuristics are Not Enough: Calibrated and Corrected Caching for Video Diffusion Acceleration

    Oct 12, 2026Jiyue Jiang, Zhiyu Huo, Yuhan Chen +3Diffusion Model CachingDiffusion Model Acceleration