AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

MAD: Modality-Adaptive Decoding for Mitigating Cross-Modal Hallucinations in Multimodal Large Language Models

Sangyun Chung, Se Yeon Kim, Youngchae Chee, Yong Man Ro

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 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
add MAD adaptive modality-weighted contrastive decodingVideoLLaMA2-AV-7B · CMM overallaccuracy (%): 73.5 -> 81.3Improved
add MADQwen2.5-Omni-7B · CMM overallaccuracy (%): 72.7 -> 81.4Improved
add MADVideoLLaMA2-AV-7B · AVHBench overallaccuracy (%): 77.4 -> 79.4Improved
add MADQwen2.5-Omni-7B · AVHBench overallaccuracy (%): 76.9 -> 81.6Improved
add VCD-Extended uniform contrastive decodingVideoLLaMA2-AV-7B · AVHBench overallaccuracy (%): 77.4 -> 70.4Hurt
add VCD-Extended to Qwen2.5-OmniQwen2.5-Omni-7B · CMM overallaccuracy (%): 72.7 -> 72.8No clear effect
add AVCD vs MADVideoLLaMA2-AV-7B · CMM overallaccuracy (%): 73.5 -> 75.8 (AVCD); 81.3 (MAD)Mixed
use adaptive weights instead of uniform weights (ablation)MAD · CMM overallaccuracy (%): 79.4 -> 81.3Improved
use soft weighting instead of argmax branch selection (ablation)MAD · CMM overallaccuracy (%): 78.7 -> 81.3Improved
add audio weight w_a (ablation)MAD · CMM overallaccuracy (%): 78.0 -> 81.3Improved
add visual weight w_v (ablation)MAD · CMM overallaccuracy (%): 78.3 -> 81.3Improved
add audio-visual weight w_av (ablation)MAD · CMM overallaccuracy (%): 78.9 -> 81.3Improved

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