AI Paper Atlas

Research map / Video / Video-language understanding

VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding

Jiapeng Shi, Junke Wang, Zuyao You, Bo He, Zuxuan Wu

ICML 2026 · Video › Video-language understanding · approach: Long video understanding · 0 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
use SlowFast tokens with joint training instead of slow-only or fast-only tokens (ablation)VideoLoom (InternVL2.5-4B) · QVHighlights / MeVISmIoU / J&F: +4.8 mIoU on QVHighlights, +3.2 J&F on MeVIS over standalone modelsImproved
joint training with slow tokens only (no fast tokens) (ablation)VideoLoom (InternVL2.5-4B) · Charades-STAR1@0.5: 66.1 -> 38.8 (vs temporal-only fast)Hurt
joint training with fast tokens only (no slow tokens) (ablation)VideoLoom (InternVL2.5-4B) · MeVISJ&F: 50.0 -> 44.6Hurt
split tokens by task (fast for temporal, slow for spatial) instead of unified SlowFast sequence (ablation)VideoLoom (InternVL2.5-4B) · QVHighlights / MeVISmIoU / J&F: QVHighlights mIoU 57.2 -> 47.1; MeVIS 50.0 -> 47.6Hurt
add LoomData-8.7k to training data (ablation)VideoLoom (InternVL2.5-4B) · LoomBench CombinedJ&F bi-fore: 36.9 -> 41.9 (+5.0)Improved
add LoomData-8.7k to training data (ablation)VideoLoom (InternVL2.5-4B) · Charades-STA / ReVOS / MME / MMBenchR1@0.5 / J&F / MME / Acc: R1@0.5 66.3 -> 67.8; ReVOS 59.9 -> 60.6; MMBench 80.9 -> 81.1Improved
add LoomData-8.7k to training data (ablation)VideoLoom · RefDavis17 (zero-shot, non-human)J&F: 67.7 -> 70.0 (+2.3)Improved
add LoomData-8.7k to training data (ablation)VideoLoom · MeVIS interaction queries (275)J&F: 63.6 -> 65.2 (+1.6)Improved
add VQA data alone without LoomData (ablation)VideoLoom (InternVL2.5-4B) · Table 6 benchmarksReVOS J&F / LoomBench J&F bi-fore: ReVOS 60.0 -> 59.9; LoomBench J&F bi-fore 34.6 -> 36.9No clear effect
scale backbone from InternVL2.5-4B to InternVL2.5-8B (ablation)VideoLoom · LoomBench CombinedJ&F bi-fore: 41.9 -> 47.2Improved
upgrade backbone from InternVL2.5-8B to InternVL3-8B (ablation)VideoLoom · LoomBench CombinedJ&F bi-fore: 47.2 -> 49.1Improved
joint model instead of cascaded TimeSuite+Sa2VA pipelineVideoLoom-8B · LoomBench CombinedtIoU / J&F bi-fore: +16.2 tIoU, +15.4 J&F bi-foreImproved

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