AI Paper Atlas

Research map / Video / Video-language understanding

OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models

Yue Ding, Yiyan Ji, Jungang Li, Xuyang Liu, Xinlong Chen, Junfei Wu, Bozhou Li, Bohan Zeng, Yang Shi, Yushuo Guan, Yuanxing Zhang, Jiaheng Liu and 3 more

ICML 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained 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
add spatial saliency to STVP (vs temporal only) (ablation)OmniSIFT · DailyOmni, WorldSenseaccuracyImproved
add temporal saliency to STVP (vs spatial only) (ablation)OmniSIFT · DailyOmni, WorldSenseaccuracyImproved
add visual guidance to audio selection (vs audio-only self-attention selector) (ablation)OmniSIFT VGAS · DailyOmni, WorldSenseaccuracy: accuracy declines of 3.9% and 2.9% on DailyOmni and WorldSenseImproved
use 1-layer instead of 3-layer VGAS selector (ablation)OmniSIFT · VideoMME, 35%accuracy: 67.2 -> 68.3Improved
use 1-layer instead of 3-layer VGAS selector (ablation)OmniSIFT · DailyOmni, 35%accuracy: 72.3 -> 73.2Improved
use 1-layer instead of 3-layer VGAS selector (ablation)OmniSIFT · WorldSense, 35%accuracy: 49.0 -> 50.0Improved
use STVP instead of random video pruning (ablation)OmniSIFT · DailyOmni, 35%accuracy: 67.8 -> 73.2Improved
use STVP instead of random video pruning (ablation)OmniSIFT · WorldSense, 35%accuracy: 47.8 -> 50.0Improved
use VGAS instead of random audio pruning (ablation)OmniSIFT · DailyOmni, 35%accuracy: 71.0 -> 73.2Improved
use VGAS instead of random audio pruning (ablation)OmniSIFT · WorldSense, 35%accuracy: 49.1 -> 50.0Improved
use cross-attention VGAS instead of SSM selector (ablation)OmniSIFT · DailyOmni, 35%accuracy: 67.3 -> 73.2Improved
use fixed instead of adaptive video budget allocation (ablation)OmniSIFT · DailyOmni, 35%accuracy: 71.9 -> 73.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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