# $\\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation

Source: [$\\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation](<https://www.sota2.com/research/paper/68fa78951e209131cea79172>)

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

Data updated: 2025-10-26T04:41:15.331Z

Authors: Saul Santos, Ant\\'onio Farinhas, Daniel C. McNamee, Andr\\'e F. T. Martins

Published: 2025-01-31T12:45:46.000Z

## Abstract

Current video-language models struggle with long-video understanding due to limited context lengths and reliance on sparse frame subsampling, often leading to information loss. This paper introduces $\\infty$-Video, which can process arbitrarily long videos through a continuous-time long-term memory (LTM) consolidation mechanism. Our framework augments video Q-formers by allowing them to process unbounded video contexts efficiently and without requiring additional training. Through continuous attention, our approach dynamically allocates higher granularity to the most relevant video segments, forming "sticky" memories that evolve over time. Experiments with Video-LLaMA and VideoChat2 demonstrate improved performance in video question-answering tasks, showcasing the potential of continuous-time LTM mechanisms to enable scalable and training-free comprehension of long videos.

## 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/2501.19098>)

[PDF](<https://arxiv.org/pdf/2501.19098.pdf>)
