OMGM
OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval (ACL 2025 Main Conference)
We provide the vqa data and knowledge bases used in OMGM. To facilitate comparison with related baselines, we use the VQA data processed by EchoSight, which involves cleaning a small number of samples missing entity images. Additionally, the knowledge base for InfoSeek is the same 100k-sample subset sampled from the E-VQA 2M knowledge base as used by EchoSight. The download links are provided below:
⚡ How to use OMGM
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/chaolinaviy-omgmCapabilities
Do you own OMGM?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.