AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Deciphering Cross-Modal Alignment in Large Vision-Language Models via Modality Integration Rate

Qidong Huang, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Yuhang Cao, Jiaqi Wang, Weiming Zhang, Nenghai Yu

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Visual instruction tuning · 4 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 MoCa learnable scale-and-shift on vision tokensLLaVA-v1.5 7B · 7-9 benchmark averageAverage score: 59.1 -> 60.6Improved
add MoCaLLaVA-v1.5 7B · MIRMIR: 3.374 -> 3.162Improved
add MoCaMini-Gemini 7B · benchmark averageAverage score: 62.1 -> 63.0Improved
add MoCaMini-Gemini 7B · MIRMIR: 2.667 -> 2.514Improved
lengthen pre-training captions from 15.2 to 181.2 tokens (ablation)LLaVA-v1.5 7B · post-SFT averageAverage score: 63.8 -> 64.4Improved
lengthen captions from 127.1 to 181.2 (ablation)LLaVA-v1.5 7B · SEED-Imgaccuracy: 67.6 -> 67.6No clear effect
lower learning rate from 3e-3 to 3e-4 (ablation)LLaVA-v1.5 7B pre-training · post-SFT averageAverage score: 58.7 -> 60.0Improved
increase warmup ratio from 3e-2 to 5e-2 (ablation)LLaVA-v1.5 7B pre-training · post-SFT averageAverage score: 59.5 -> 59.6No clear effect
use linear instead of cosine LR scheduler (ablation)LLaVA-v1.5 7B pre-training · post-SFT averageAverage score: 59.5 -> 59.5No clear effect
unlock entire LLM during pre-training instead of projector only (ablation)LLaVA-v1.5 7B, ~1.9M data · post-SFT averageAverage score: 64.0 -> 65.9Improved
unlock former half of LLM instead of projector only (ablation)LLaVA-v1.5 7B, ~1.9M data · post-SFT averageAverage score: 64.0 -> 65.9Improved
unlock LoRA on LLM with merge instead of projector only (ablation)LLaVA-v1.5 7B, ~1.9M data · post-SFT averageAverage score: 64.0 -> 64.5Improved

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