Official code for "Vision Transformers with Self-Distilled Registers" (NeurIPS 2025 Spotlight)
- Updated
Oct 19, 2025 - Jupyter Notebook
Official code for "Vision Transformers with Self-Distilled Registers" (NeurIPS 2025 Spotlight)
A hybrid vector search using a mixture of sparse and dense vectors using Qdrant.
A modular and open-source RAG-ready Embedding API supporting dense, sparse and Reranking Models. Easily configurable via config.yaml — no code changes required.
Add a description, image, and links to the dense-embeddings topic page so that developers can more easily learn about it.
To associate your repository with the dense-embeddings topic, visit your repo's landing page and select "manage topics."