FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding

TL;DR

FluxMem introduces an adaptive hierarchical memory framework that efficiently compresses visual information in streaming videos, achieving state-of-the-art results with reduced latency and memory usage.

Contribution

It proposes a novel, training-free, adaptive hierarchical memory system for streaming video understanding, combining temporal and spatial compression without manual tuning.

Findings

Achieves 76.4 on StreamingBench and 67.2 on OVO-Bench in real-time.

Reduces latency by 69.9% and GPU memory by 34.5%.

Maintains strong offline performance with 73.1 on MLVU using fewer tokens.

Abstract

This paper presents FluxMem, a training-free framework for efficient streaming video understanding. FluxMem adaptively compresses redundant visual memory through a hierarchical, two-stage design: (1) a Temporal Adjacency Selection (TAS) module removes redundant visual tokens across adjacent frames, and (2) a Spatial Domain Consolidation (SDC) module further merges spatially repetitive regions within each frame into compact representations. To adapt effectively to dynamic scenes, we introduce a self-adaptive token compression mechanism in both TAS and SDC, which automatically determines the compression rate based on intrinsic scene statistics rather than manual tuning. Extensive experiments demonstrate that FluxMem achieves new state-of-the-art results on existing online video benchmarks, reaching 76.4 on StreamingBench and 67.2 on OVO-Bench under real-time settings, while reducing latency by 69.9% and peak GPU memory by 34.5% on OVO-Bench. Furthermore, it maintains strong offline performance, achieving 73.1 on MLVU while using 65% fewer visual tokens.