AI Paper Atlas

Research map / Video / Video-language understanding

StreamingTOM: Streaming Token Compression for Efficient Video Understanding

Xueyi Chen, Keda Tao, Kele Shao, Huan Wang

CVPR 2026 · Video › Video-language understanding · approach: Long video understanding · 35 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use 50 tokens per frame instead of 40 (ablation)StreamingTOM · VideoMME overall (4-bit)accuracy: 58.9 -> 59.9Improved
use 50 tokens per frame instead of 60 (ablation)StreamingTOM · VideoMME overall (4-bit)accuracy: 59.3 -> 59.9Improved
use 4-bit instead of 2-bit quantization (ablation)StreamingTOM · VideoMME overall (50 tokens)accuracy: 58.5 -> 59.9Improved
add Causal Temporal Reduction (50 tokens per frame) pre-LLMStreamingTOM · Prefill time, 64 framesprefill ms: 337.8 -> 92.8Improved
use pre-LLM reduction plus 4-bit memory instead of post-LLM kv compression (LiveVLM)StreamingTOM · Offline benchmarks averageaccuracy: 60.9 -> 63.8Improved
compare with full LLaVA-OV-7B offlineStreamingTOM · Offline benchmarks averageaccuracy: 61.0 -> 63.8Improved
no CPU offloading versus ReKV with CPU offloadingStreamingTOM · RVS averageaccuracy: 59.0 -> 55.8Hurt
compare against StreamMemStreamingTOM · RVS averageaccuracy: 55.2 -> 55.8No clear effect

Later papers that compared with this method

1 later accepted paper reports StreamingTOM as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy