pith. sign in

In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022), arXiv:2206.01720 4

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Linear Scaling Video VLMs for Long Video Understanding

cs.CV · 2026-05-29 · unverdicted · novelty 5.0

StateKV is an inference-time technique that replaces quadratic self-attention prefill in video VLMs with a fixed-capacity importance-based recurrent state, keeping accuracy near full attention on long-video benchmarks without retraining.

citing papers explorer

Showing 1 of 1 citing paper.

  • Linear Scaling Video VLMs for Long Video Understanding cs.CV · 2026-05-29 · unverdicted · none · ref 8

    StateKV is an inference-time technique that replaces quadratic self-attention prefill in video VLMs with a fixed-capacity importance-based recurrent state, keeping accuracy near full attention on long-video benchmarks without retraining.