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
Haon-Chen
AI & ML interests
None yet
Organizations
models 5
Haon-Chen/e5-omni-3B
Visual Document Retrieval • 5B • Updated • 364 • 6
Haon-Chen/e5-omni-7B
Visual Document Retrieval • 9B • Updated • 36.8k • 8
Haon-Chen/speed-embedding-7b-instruct
Feature Extraction • 7B • Updated • 70 • 5
Haon-Chen/speed-synthesis-8b-revisor
Text Generation • 8B • Updated • 2
Haon-Chen/speed-synthesis-8b-senior
Text Generation • 8B • Updated • 18 •