AI Paper Atlas

Research map / Video / Video-language understanding

StreamReady: Learning What to Answer and When in Long Streaming Videos

Shehreen Azad, Vibhav Vineet, Yogesh S Rawat

CVPR 2026 · Video › Video-language understanding · approach: Video question answering · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
add readiness mechanism (<RDY> token + head) (ablation)StreamReady · ProReady-QA (REC)ARS: 0.48 -> 0.68Improved
add readiness mechanism to trivial reasoning (ablation)Trivial reasoning baseline · ProReady-QA (REC)ARS: 0.44 -> 0.50Improved
add trivial reasoning to baseline (ablation)Qwen-2-VL · ProReady-QA (REC)accuracy: 20.7 -> 28.7Improved
add memory storage and query-aware reasoning (ablation)StreamReady · ProReady-QA (REC)accuracy: 28.7 -> 39.4Improved
use <RDY> token with MLP head instead of MLP only (ablation)StreamReady · ProReady-QA (REC)ARS: 0.52 -> 0.68Improved
use Transformer head instead of MLP head (ablation)StreamReady · ProReady-QA (REC)ARS: 0.68 -> 0.69No clear effect
place <RDY> on learned long-term representation instead of long-term input (ablation)StreamReady · ProReady-QA (REC)ARS: 0.54 -> 0.68Improved
add long-term memory to short-term memory (ablation)StreamReady · ProReady-QA (REC)accuracy: 12.7 -> 37.6Improved
add contextual memory (ablation)StreamReady · StreamingBench (contextual)accuracy: 32.1 -> 48.2Improved
use hierarchical adaptive clustering instead of flat similarity memory (ablation)StreamReady · ProReady-QA (CTD)accuracy: 32.2 -> 43.5Improved
add query-aware reasoning (ablation)StreamReady · ProReady-QA (CTD)accuracy: 22.8 -> 43.5Improved
use coarse-to-fine instead of prototype-only long-term awareness (ablation)StreamReady · ProReady-QA (REC)ARS: 0.44 -> 0.68Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

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