The official code of "Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval"
-
Updated
Aug 7, 2026 - Python
The official code of "Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval"
Mono-Kit is a multimodal library that projects text, images, audio, and video into a shared embedding space, featuring a custom vector database for unified similarity search
A novel DR visualization technique for interactive exploration of multimodal embeddings through Dynamic Kernel enhanced projection.
All-in-one inference box for vec* family projects. Supports Qwen3-VL multimodal embedding
Add a description, image, and links to the multimodal-embedding topic page so that developers can more easily learn about it.
To associate your repository with the multimodal-embedding topic, visit your repo's landing page and select "manage topics."