AI Paper Atlas

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

MuCo: Multi-turn Contrastive Learning for Multimodal Embedding Model

Geonmo Gu, Byeongho Heo, Jaemyung Yu, Jaehui Hwang, Taekyung Kim, Sangmin Lee, HeeJae Jun, Yoohoon Kang, Sangdoo Yun, Dongyoon Han

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment · 2 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
scale turns to 7 per image at fixed batch 1024 instead of scaling batch size (ablation)MuCo-2B · MMEB zero-shotPrecision@1: 57.5 -> 58.2 with 18.0 vs 122.7 PFLOPsImproved
increase single-turn batch size 1024 to 8192 (ablation)single-turn baseline · MMEB zero-shotPrecision@1: 57.1 -> 57.8Improved
add compounded supervision (turns attend to earlier turns) (ablation)MuCo-2B · MMEB fine-tunedPrecision@1: 68.4 -> 69.5Improved
add logit masking of same-image pairs during fine-tuning (ablation)MuCo-2B · MMEB fine-tunedPrecision@1: 30.9 -> 69.5Improved
add logit masking in pretraining (ablation)MuCo-2B · MMEB fine-tunedPrecision@1: 69.2 -> 69.5Improved
use multi-turn MuCo pretraining instead of single-turn on mmE5 data (ablation)MuCo-2B · MMEB fine-tunedPrecision@1: 68.6 -> 69.0Improved
add M3T pretraining at 5M scale (ablation)MuCo-2B · MMEB fine-tunedPrecision@1: 68.5 -> 69.5Improved
pretrain on MegaPairs 26M single-turn (ablation)MuCo-2B · MMEB zero-shotPrecision@1: 55.6 (mmE5) -> 41.5Hurt
add each task category in data (cumulative: classification, global, local, creative VQA) (ablation)MuCo-2B pretraining · MMEB zero-shotOverall: 55.1 -> 58.2Improved
use 50% counterpart masking vs 25% or 75% (ablation)MuCo-2B fine-tuning · MMEB fine-tunedPrecision@1: 69.3/68.9 -> 69.5Improved
add reconstruction guidance prompt vs none (ablation)MuCo-2B fine-tuning · MMEB fine-tunedPrecision@1: 69.0 -> 69.5Improved
swap image captioner BLIP-Large for Qwen2-VL-7B (ablation)MuCo-2B fine-tuning · MMEB fine-tunedPrecision@1: 69.4 vs 69.5No 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