# Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs

Source: [Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs](<https://www.sota2.com/research/paper/68fa7c5a1e209131cea8db62>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T10:39:22.570Z

Authors: Vaggelis Dorovatas, Soroush Seifi, Gunshi Gupta, Rahaf Aljundi

Published: 2025-10-20T10:04:49.000Z

## Abstract

Video Large Language Models (Video-LLMs) excel at understanding videos in-context, provided they have full access to the video when answering queries. However, these models face challenges in streaming scenarios where hour-long videos must be processed online, and questions need timely responses. In this work, we propose a training-free approach compatible with standard Video-LLMs, leveraging three key concepts: 1) LLM-informed selection of visual tokens to identify those that the LLM has attended to and contributed to its understanding of each short clip. Our attention-based selection allows us to discard up to ~95% of unimportant visual tokens with minimal performance loss; 2) Recurrent processing of past selected tokens to generate temporally coherent understanding of each processed clip; 3) Caption-based question answering for lightweight and accurate responses. Our method achieves state-of-the-art performance on streaming video benchmarks, striking a balance between efficiency and effectiveness.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.17364>)

[PDF](<https://arxiv.org/pdf/2510.17364.pdf>)
