A lightweight explicit alignment recipe that adapts off-the-shelf VLMs into robust omni-modal embedding models. https://arxiv.org/abs/2601.03666
Haonan Chen PRO
Haon-Chen
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 11 hours ago
e5-omni: Explicit Cross-modal Alignment for Omni-modal Embeddings
updated
a collection
about 13 hours ago
e5-omni
submitted
a paper
about 13 hours ago
e5-omni: Explicit Cross-modal Alignment for Omni-modal Embeddings
Organizations
models
5
Haon-Chen/e5-omni-7B
Visual Document Retrieval
•
9B
•
Updated
•
63
Haon-Chen/e5-omni-3B
Visual Document Retrieval
•
5B
•
Updated
•
168
Haon-Chen/speed-embedding-7b-instruct
Feature Extraction
•
7B
•
Updated
•
158
•
5
Haon-Chen/speed-synthesis-8b-revisor
Text Generation
•
8B
•
Updated
•
5
Haon-Chen/speed-synthesis-8b-senior
Text Generation
•
8B
•
Updated
•
7