AI Paper Atlas

Research map / Video / Video-language understanding

TIME: Temporal-Sensitive Multi-Dimensional Instruction Tuning and Robust Benchmarking for Video-LLMs

Yunxiao Wang, Meng Liu, Wenqi Liu, Xuemeng Song, Bin Wen, Fan Yang, Tingting Gao, Di Zhang, Guorui Zhou, Liqiang Nie

AAAI 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
fine-tune with TIME dataset and MTPVideo-LLaVA · TIMEBench (AVG)accuracy: 27.3 -> 31.4Improved
fine-tune with TIME dataset and MTPVideoLLaMA 2 · TIMEBench (AVG)accuracy: 27.4 -> 32.8Improved
fine-tune with TIME dataset and MTPShareGPT4Video · TIMEBench (AVG)accuracy: 33.7 -> 35.6Improved
fine-tune with TIME dataset and MTPInternVL 2.5 · TIMEBench (AVG)accuracy: 34.4 -> 35.7Improved
fine-tune with TIME dataset and MTPInternVL 2.5 · MVBenchaccuracy: 72.1 -> 71.9No clear effect
fine-tune with TIME dataset and MTPInternVL 2.5 · Video-MMEaccuracy: 59.6 -> 59.0Hurt
fine-tune with TIME dataset and MTPVideoLLaMA 2 · TempCompassaccuracy: 44.2 -> 58.2Improved
add TIME dataset alone (ablation)VideoLLaMA 2 · TIMEBench (AVG)accuracy: 27.4 -> 32.6Improved
add MTP alone (ablation)VideoLLaMA 2 · TIMEBench (AVG)accuracy: 27.4 -> 29.5Improved
add MTP on top of TIME (ablation)VideoLLaMA 2 · TIMEBench (AVG)accuracy: 32.6 -> 32.8Improved
mix TIME with original data instead of adding it after (ablation)VideoLLaMA 2 · TIMEBench (AVG)accuracy: 26.6 -> 32.6Improved
mix TIME with original data instead of adding it before (ablation)VideoLLaMA 2 · TIMEBench (AVG)accuracy: 28.7 -> 32.6Improved

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