AI Paper Atlas

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

TextME: Bridging Unseen Modalities Through Text Descriptions

Soyeon Hong, Jinchan Kim, Jaegook You, Seungtaek Choi, Suha Kwak, Hyunsouk Cho

ICML 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 offset (centroid) correction (ablation)TextME · ModelNet40Top-1: 4.05 -> 70.86Improved
add offset (centroid) correction (ablation)TextME · AudioCapsR@1: 8.68 -> 15.35Improved
add offset correction on molecules (gap consistency 0.78) (ablation)TextME · DrugBankMRR: 36.44 -> 34.75Hurt
train projection on domain captions instead of general all-NLI text (ablation)TextME · ModelNet40Top-1: 12.10 -> 70.86Improved
train projection on domain captions instead of general all-NLI text (ablation)TextME · DrugBankMRR: 16.10 -> 34.75Improved
use LLM embedding anchor instead of multimodal encoder anchor (ablation)TextME · AudioCapsR@1: 14.5 -> 16.2 (NV-Embed-v2 vs LanguageBind)Improved
use LLM embedding anchor instead of multimodal encoder anchor (ablation)TextME · ESC-50Top-1: 86.7 -> 77.2 (CLIP vs Qwen3-Embed)Hurt
ensemble multiple anchors by score-level late fusion (ablation)TextME · AudioCapsR@1: 15.4 -> 19.2Improved
ensemble multiple anchors by score-level late fusion (ablation)TextME · RSNATop-1: 46.6 -> 46.9No clear effect
lower variance of gap-content orthogonality in the encoderTextME · all tasks (33 data points)performance preservation: Pearson r = -0.67, p < 0.001Improved
use TextME instead of unpaired COX baselineTextME · COCO retrievalrecall: 0.02 -> 28.63Improved

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