English

Inference Compute-Optimal Video Vision Language Models

Computer Vision and Pattern Recognition 2025-05-27 v1 Computation and Language

Abstract

This work investigates the optimal allocation of inference compute across three key scaling factors in video vision language models: language model size, frame count, and the number of visual tokens per frame. While prior works typically focuses on optimizing model efficiency or improving performance without considering resource constraints, we instead identify optimal model configuration under fixed inference compute budgets. We conduct large-scale training sweeps and careful parametric modeling of task performance to identify the inference compute-optimal frontier. Our experiments reveal how task performance depends on scaling factors and finetuning data size, as well as how changes in data size shift the compute-optimal frontier. These findings translate to practical tips for selecting these scaling factors.

Keywords

Cite

@article{arxiv.2505.18855,
  title  = {Inference Compute-Optimal Video Vision Language Models},
  author = {Peiqi Wang and ShengYun Peng and Xuewen Zhang and Hanchao Yu and Yibo Yang and Lifu Huang and Fujun Liu and Qifan Wang},
  journal= {arXiv preprint arXiv:2505.18855},
  year   = {2025}
}

Comments

Annual Meeting of the Association for Computational Linguistics (ACL), 2025

R2 v1 2026-07-01T02:36:24.978Z