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
new activity about 7 hours ago
Haon-Chen/e5-omni-7B:Integrate with Sentence Transformers v5.4 new activity about 7 hours ago
Haon-Chen/e5-omni-3B:Integrate with Sentence Transformers v5.4 upvoted a paper about 2 months ago
DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual HistoriesOrganizations
models 5
Haon-Chen/e5-omni-7B
Visual Document Retrieval • 9B • Updated • 410 • 5
Haon-Chen/e5-omni-3B
Visual Document Retrieval • 5B • Updated • 142 • 4
Haon-Chen/speed-embedding-7b-instruct
Feature Extraction • 7B • Updated • 118 • 5
Haon-Chen/speed-synthesis-8b-revisor
Text Generation • 8B • Updated • 6
Haon-Chen/speed-synthesis-8b-senior
Text Generation • 8B • Updated • 5