Paper Detail

Linear Scaling Video VLMs for Long Video Understanding

Cristobal Eyzaguirre, Jiajun Wu, Juan Carlos Niebles

arxiv Score 3.8

Published 2026-05-29 · First seen 2026-06-01

General AI

Abstract

Video vision-language models (VLMs) are increasingly used in long-horizon and streaming settings, yet most video encoders still rely on spatiotemporal self-attention, causing compute and latency to grow quadratically with the number of frames. Existing efficiency methods improve scalability but often lose accuracy relative to full self-attention, for example through aggressive frame/token dropping or coarse attention approximations. We introduce StateKV, an inference-time method that adapts pretrained long-video VLMs to linear-time video prefill by carrying cross-frame context in a fixed-capacity, importance-based recurrent state, paired with a second full per-frame cache used for decoding. Across three long-video benchmarks and seven models spanning three families and multiple scales, StateKV remains close to full self-attention and consistently outperforms dominant sliding-window / recency-based streaming approximations, without fine-tuning or architectural changes. StateKV also reduces video-prefill cost measured FLOPs, enabling stronger accuracy at a fixed compute budget by running larger models. These results suggest a practical step toward scalable long-video understanding.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{eyzaguirre2026linear,
  title = {Linear Scaling Video VLMs for Long Video Understanding},
  author = {Cristobal Eyzaguirre and Jiajun Wu and Juan Carlos Niebles},
  year = {2026},
  abstract = {Video vision-language models (VLMs) are increasingly used in long-horizon and streaming settings, yet most video encoders still rely on spatiotemporal self-attention, causing compute and latency to grow quadratically with the number of frames. Existing efficiency methods improve scalability but often lose accuracy relative to full self-attention, for example through aggressive frame/token dropping or coarse attention approximations. We introduce StateKV, an inference-time method that adapts pret},
  url = {https://arxiv.org/abs/2605.31598},
  keywords = {cs.CV},
  eprint = {2605.31598},
  archiveprefix = {arXiv},
}

Metadata

{}