AI Paper Atlas

Research map / Video / Video-language understanding

EchoBat: Echo-Vision Enhancement and Echo-Layered Sampling for Video LLMs Hallucination Mitigation

Shuai Liu, Da Chen, Yiheng Pan, Chenwei Tian, Qian Li, Chenhao Lin

AAAI 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 Echo-Vision Enhancement (audio-aided preference pairs, DPO) (ablation)LLaVA-Video-7B · VideoHallucer (Ovr)accuracy: 45.9 -> 46.3Improved
add Echo-Layered Sampling on top of EVE (ablation)LLaVA-Video-7B · VideoHallucer (Ovr)accuracy: 46.3 -> 46.9Improved
add Video Reverse Non-preference on top of EVE+ELS (ablation)LLaVA-Video-7B · VideoHallucer (Ovr)accuracy: 46.9 -> 47.2Improved
add Echo-Layered Sampling on top of EVE (ablation)LLaVA-Video-7B · CMM video VLCorrperception accuracy: 89.0 -> 90.5Improved
add Video Reverse Non-preference (ablation)LLaVA-Video-7B · CMM video VLCorrperception accuracy: 90.5 -> 92.0Improved
apply full EchoBat DPO (ablation)LLaVA-Video-7B · CMM video LangDominancehallucination resistance: 74.0 -> 76.0Improved
apply EchoBatLLaVA-Video-7B · MSVD-QAaccuracy: 82.1 -> 83.7Improved
apply EchoBatLLaVA-Video-7B · MSR-VTT QAaccuracy: 69.7 -> 71.2Improved
apply EchoBatLLaVA-Onevision-7B · VideoHallucer (Bas)accuracy: 60.9 -> 62.3Improved
apply EchoBatLLaVA-Video-7B · VideoChatGPT-Bench Temporalscore: 2.2 -> 2.8Improved
use tau 0.6 instead of 0.4 for audio filtering threshold (ablation)EchoBat · EventHallusionaccuracy: -4.1%Hurt

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