AI Paper Atlas

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

Augmenting Intra-Modal Understanding in MLLMs for Robust Multimodal Keyphrase Generation

Jiajun Cao, Qinggang Zhang, Yunbo Tang, Zhishang Xiang, Chang Yang, Jinsong Su

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment · 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 AimKP (progressive masking and gradient filtering) to LLaVA-1.5-7BLLaVA-1.5-7B · CMKP multimodal inputF1@1: 61.58 -> 63.16Improved
add AimKP to Qwen2-VL-7BQwen2-VL-7B · CMKP multimodal inputMAP@5: 69.89 -> 71.00Improved
add AimKP to LLaVA-1.5-7BLLaVA-1.5-7B · CMKP image-only inputMAP@5: 37.68 -> 41.94Improved
add AimKP to LLaVA-1.5-7BLLaVA-1.5-7B · CMKP text-only inputMAP@5: 53.92 -> 55.45Improved
add AimKP to LLaVA-1.5-7BLLaVA-1.5-7B · CMKP multimodal inputF1@3: 37.90 -> 39.00Improved
add progressive masking on text modality (ablation)AimKP (LLaVA-1.5-7B) · CMKP multimodal inputMAP@5: 69.12 -> 69.96Improved
add progressive masking on image modality (ablation)AimKP (LLaVA-1.5-7B) · CMKP multimodal inputMAP@5: 69.43 -> 69.96Improved
add gradient-based filtering of masked samples (ablation)AimKP (LLaVA-1.5-7B) · CMKP multimodal inputF1@1: 62.79 -> 63.16Improved
use progressive masking instead of fixed stride 2 (ablation)AimKP (LLaVA-1.5-7B) · CMKP multimodal inputMAP@5: 69.93 -> 69.96Improved
use progressive masking instead of fixed stride 4 (ablation)AimKP (LLaVA-1.5-7B) · CMKP multimodal inputF1@3: 38.61 -> 39.00Improved
use alternative loss weighting strategies for auxiliary losses (ablation)AimKP · CMKPkeyphrase qualityNo clear effect

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