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
Recent Activity
upvoted a paper about 20 hours ago
Douyin Multimodal Embedding Model Technical Report submitted a paper about 20 hours ago
Douyin Multimodal Embedding Model Technical Report authored a paper 4 days ago
Douyin Multimodal Embedding Model Technical ReportOrganizations
models 5
Haon-Chen/e5-omni-3B
Visual Document Retrieval • 5B • Updated • 398 • 6
Haon-Chen/e5-omni-7B
Visual Document Retrieval • 9B • Updated • 34.2k • 9
Haon-Chen/speed-embedding-7b-instruct
Feature Extraction • 7B • Updated • 273 • 5
Haon-Chen/speed-synthesis-8b-revisor
Text Generation • 8B • Updated • 3
Haon-Chen/speed-synthesis-8b-senior
Text Generation • 8B • Updated • 8 •