AI Paper Atlas

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

SOLAR: Self-supervised Joint Learning for Symmetric Multimodal Retrieval

Wenjie Yang, Hang Yu, Yuyu Guo, Peng Di

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 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 disentanglement (masked ITC with GLA, GD, LD) instead of plain contrastive alignment only (ablation)SOLAR-B+D · sym-MM2MMAvg: 81.5 -> 86.5Improved
add masked ITC loss (ablation)SOLAR-B+D · sym-MM2MMAvg: 82.6 -> 86.5Improved
add global-to-local alignment loss (ablation)SOLAR-B+D · sym-MM2MMAvg: 80.8 -> 86.5Improved
add global unimodal distillation (ablation)SOLAR-B+D · sym-MM2MMAvg: 84.9 -> 86.5Improved
add local unimodal distillation (ablation)SOLAR-B+D · sym-MM2MMAvg: 82.4 -> 86.5Improved
add evolutionary mask schedule (ablation)SOLAR-B+D · sym-MM2MMAvg: 86.0 -> 86.5Improved
use annealed evolutionary mask instead of static hard mask (ablation)SOLAR-B+D · sym-MM2MMAvg: 84.8 -> 86.5Improved
add projection heads (ablation)SOLAR-B+D · sym-MM2MMAvg: 82.6 -> 86.5Improved
add Stage 2 self-supervised contrastive training after Stage 1 (ablation)SOLAR-B+D · sym-MM2MMAvg: 82.2 -> 86.5Improved
add constructed negatives (masking the difference set) (ablation)SOLAR-B+D · sym-MM2MMAvg: 84.0 -> 86.5Improved
mask the semantic intersection for positives instead of random masking (ablation)SOLAR-B+D · sym-MM2MMAvg: 83.3 -> 86.5Improved
use semantic segmentation masking instead of patch-level masking (ablation)SOLAR-B+D · sym-MM2MMAvg: 81.5 -> 86.5Improved

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