AI Paper Atlas

Research map / Video / Video-language understanding

PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance

Shangkun Sun, Ruyang Liu, Haoran Tang, Yixiao Ge, Haibo Lu, Jiankun Yang, Chen Li

ICLR 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 21 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 prompt-guided pooling (1024 tokens) in place of average pooling (ablation)LLaVA-Next · Video-MME (w/ subs)accuracy: 43.4 -> 48.9Improved
add prompt-guided pooling instead of feeding all 4608 tokens (ablation)LLaVA-Next · Video-MME (w/ subs)accuracy: 47.4 -> 48.9Improved
add CLIP context extension (ablation)PPLLaVA (LLaVA-Next) · Video-MME (w/ subs) overallaccuracy: 48.9 -> 50.0Improved
add CLIP context extension (ablation)PPLLaVA (LLaVA-Next) · VCG-Bench averagescore: 3.21 -> 3.32Improved
use weighted average pooling instead of separate spatiotemporal pooling (ablation)PPLLaVA · Video-MME (w/ subs)accuracy: 44.1 -> 53.6Improved
use weighted average pooling instead of max pooling (ablation)PPLLaVA · Video-MME (w/ subs)accuracy: 52.0 -> 53.6Improved
use weighted average pooling instead of Token Merging (ablation)PPLLaVA · Video-MME (w/ subs)accuracy: 51.9 -> 53.6Improved
use multiple pooling kernels instead of a single weighted-average kernel (ablation)PPLLaVA · Video-MME (w/ subs)accuracy: 53.6 -> 53.2No clear effect
manually select key frames instead of average sampling on redundant videosPPLLaVA · Video-MME-redundaccuracy: 47.6 -> 50.5Improved
increase pooling kernel and stride in temporal dimensionPPLLaVA · Video-MMEaccuracyHurt
increase spatial pooling kernel and stridePPLLaVA · Video-MMEaccuracyNo clear effect
apply PPLLaVA pooling to image LLMLLaVA-Next-7B · MMMU (val)accuracy: 35.8 -> 37.9Improved

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