AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

FAM: Fine-Grained Alignment Matters in Multimodal Embedding Learning with Large Vision-Language Models

Tianhang Xiang, Yirui Li, Lizhao Liu, Hongyan Zhi, Chuanshen Chen, Qing Du, Mingkui Tan

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Fine-grained improvements to CLIP · 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 MAC to VLM2Vec (ablation)VLM2Vec Qwen2-VL-2B · MMEB (Qwen2-VL-2B)average score: 55.0 -> 56.4Improved
add VEIN to VLM2Vec (ablation)VLM2Vec Qwen2-VL-2B · MMEB (Qwen2-VL-2B)average score: 55.0 -> 55.9Improved
add VEIN on top of MAC (ablation)FAM · MMEB (Qwen2-VL-2B)average score: 56.4 -> 57.3Improved
add MAC on top of VEIN (ablation)FAM · MMEB (Qwen2-VL-2B)average score: 55.9 -> 57.3Improved
add extra alignment image-text data as retrieval data instead of MAC (ablation)VLM2Vec · MMEB (Qwen2-VL-2B)average score: 55.0 -> 55.3No clear effect
use MAC training strategy rather than plain extra data (ablation)VLM2Vec · MMEB (Qwen2-VL-2B)average score: 55.3 -> 56.4Improved
add coarse-to-fine loss Lc2f to Lc (ablation)MAC alignment stage · MMEB (Qwen2-VL-2B) alignment onlyaverage score: 34.0 -> 35.3Improved
add fine-grained loss Lf (ablation)MAC alignment stage · MMEB (Qwen2-VL-2B) alignment onlyaverage score: 35.3 -> 35.4Improved
add Lc2f to Lc (ablation)MAC, full pipeline · MMEB (Qwen2-VL-2B) align + adaptaverage score: 55.8 -> 56.1Improved
add Lf to Lc and Lc2f (ablation)MAC, full pipeline · MMEB (Qwen2-VL-2B) align + adaptaverage score: 56.1 -> 56.4Improved
apply VEIN at all layers instead of none (ablation)VLM2Vec · MMEB (Qwen2-VL-2B)average score: 55.0 -> 54.2Hurt
apply VEIN at last three layers instead of last layer only (ablation)VEIN · MMEB (Qwen2-VL-2B)average score: 55.3 -> 55.9Improved

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