works on
embedding space 1modality specialist fusion 1multi-modal rehearsal 1omni-modal retrieval 1projector drift 1

From the 1 of 11 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.MMShow all

1 paper · 1 filter

cs.MM2026

Conan-embedding-v3: Fusing Modality-Specific Models for Omni-Modal Embedding

Shiyu Li, Zhiyuan Hu, Yifan Wang +3

The paper presents Conan-embedding-v3, a framework that trains modality‑specific specialist models, fuses them into a single dense backbone, and then recovers the modality projecto…