AI Paper Atlas

Research map / Video / Video-language understanding

Unstitching the Chimera: Frame-Level Risk and Train-Free Mitigation for Video Hallucination

Songyuan Yang, Guijian Tang, Kun Hu, Haotian Wang, Shixuan Liu, Wenjing Yang, Long Lan, Huibin Tan

CVPR 2026 · Video › Video-language understanding · approach: Long video understanding

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
apply train-free CH-M mitigation at inference6 VideoLLMs (7B) · 9 video benchmarksAccuracy: +1.0 to +5.6 points across models and benchmarksImproved
apply CH-MVideo-LLaVA-7B · VidHallucAccuracy: 40.3 -> 45.9Improved
apply CH-M6 VideoLLMs (7B) · Risk diagnosticsCH-Risk: 0.33 -> 0.23 (Video-LLaVA-7B)Improved
add pathway alignment term (lambda=0.3) to sSAFR (ablation)sSAFR on LLaVA-Video-7B · NExT-QAAccuracy: 74.2 -> 74.7Improved
add segment prior (gamma=0.4) to sSAFR (ablation)sSAFR on LLaVA-Video-7B · NExT-QAAccuracy: 73.9 -> 74.7Improved
use event segments instead of uniform windows in sSAFR (ablation)sSAFR on LLaVA-Video-7B · NExT-QAAccuracy: 73.5 -> 74.7Improved
add sSAFR alone (ablation)LLaVA-Video-7B · VidHallucAccuracy: 76.6 -> 79.3Improved
add RTC alone (hard cap rho=3) (ablation)LLaVA-Video-7B · NExT-QAAccuracy: 73.2 -> 73.6Improved
add RTC after sSAFR (ablation)LLaVA-Video-7B · NExT-QAAccuracy: 74.7 -> 75.1Improved
apply sSAFR before RTC rather than reversed order (ablation)CH-M on LLaVA-Video-7B · VidHallucAccuracy: 79.7 -> 80.2Improved
set coverage alpha to 0.8 rather than 0.7 or 0.9 (ablation)CH-M · NExT-QA and VidHallucDelta AccuracyImproved
set RTC cap rho to 3 rather than smaller or larger (ablation)CH-M · NExT-QA and VidHallucDelta AccuracyImproved

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