AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Learning to Mask: Cross-Modal Noise Modulation for Hallucination Mitigation in Multi-modal Large Language Models

Zijian Song, Chunlei Wang, Kun He

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Decoding-time hallucination mitigation · 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 Image Noise Modulation Module (In-Mod) (ablation)LLaVA-1.5-7B · CHAIR (MSCOCO, 64 tokens)CHAIRs: 21.20 -> 12.80Improved
add Text Noise Modulation Module (Tn-Mod) (ablation)LLaVA-1.5-7B · CHAIR (MSCOCO, 64 tokens)CHAIRs: 21.20 -> 20.40Improved
add Tn-Mod on top of In-Mod (ablation)LLaVA-1.5-7B · CHAIR (MSCOCO, 64 tokens)CHAIRs: 12.80 -> 7.60Improved
add In-Mod to MiniGPT-4 (ablation)MiniGPT-4-7B · CHAIR (MSCOCO, 64 tokens)CHAIRs: 32.40 -> 20.80Improved
add Tn-Mod to MiniGPT-4 (ablation)MiniGPT-4-7B · CHAIR (MSCOCO, 64 tokens)CHAIRs: 32.40 -> 23.00Improved
add both modulation modules to MiniGPT-4 (ablation)MiniGPT-4-7B · CHAIR (MSCOCO, 64 tokens)CHAIRs: 32.40 -> 16.20Improved
add dynamical regularization term (ablation)HalMask LLaVA-1.5-7B · POPE (average)F1: 87.11 -> 87.52Improved
add dynamical regularization term, recall (ablation)HalMask LLaVA-1.5-7B · POPE (average)recall: 82.76 -> 84.98Improved
add dynamical regularization term, RTD (ablation)HalMask LLaVA-1.5-7B · POPE (average)RTD (lower better): 56.13 -> 50.15Improved
apply HalMask to LLaVA-1.5 on CHAIRLLaVA-1.5-7B · CHAIR (MSCOCO, 64 tokens)BLEU: 16.25 -> 19.48Improved
apply HalMask to Qwen2.5-VLQwen2.5-VL-7B · CHAIR (MSCOCO, 512 tokens)CHAIRs: 36.1 -> 23.7Improved
apply HalMask to LLaVA-1.5 on AMBER CoverLLaVA-1.5-7B · AMBERCover: 50.9 -> 50.1Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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