AI Paper Atlas

Research map / Video / Video-language understanding

DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression

Bingzhou Li, Tao Huang

ECCV 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 6 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 DASH at 25% retention instead of OmniZip at 35%Qwen2.5-Omni-7B · AVUT avgaccuracy: 60.6 -> 60.9Improved
use DASH at 25% retention instead of OmniZip at 35%Qwen2.5-Omni-7B · WorldSense avgaccuracy: 44.7 -> 44.9Improved
use DASH at 25% retention instead of OmniZip at 35%Qwen2.5-Omni-3B · WorldSense avgaccuracy: 44.1 -> 44.6Improved
use DASH at 25% retention instead of OmniZip at 35%Qwen2.5-Omni-3B · AVUT avgaccuracy: 58.7 -> 58.8No clear effect
use DASH at 25% retention instead of OmniZip at 35%Qwen2.5-Omni-3B · VideoMME w/o subtitlesaccuracy: 61.9 -> 61.7Hurt
use DASH at 35% retention instead of OmniZip at 35%Qwen2.5-Omni-7B · AVUT avgaccuracy: 60.6 -> 61.5Improved
add tri-signal fusion to static grouping (ablation)OmniZip-style static grouping (3B, 25% retention) · WorldSense avgaccuracy: 44.1 -> 44.4Improved
add dynamic semantic chunking with attention-only selection (ablation)OmniZip-style static grouping (3B, 25% retention) · WorldSense avgaccuracy: 44.1 -> 44.4Improved
combine dynamic chunking and tri-signal fusion (ablation)DASH (3B, 25% retention) · WorldSense avgaccuracy: 44.4 -> 44.6Improved
use cosine similarity instead of dot product for boundary detection (ablation)DASH (3B, 25% retention) · WorldSense avgaccuracy: 43.6 -> 44.6Improved
use cosine boundaries instead of random boundaries (ablation)DASH (3B, 25% retention) · WorldSense avgaccuracy: 43.8 -> 44.6Improved
use cosine instead of change rate for boundary detection (ablation)DASH (3B, 25% retention) · WorldSense avgaccuracy: 44.0 -> 44.6Improved

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