RenderRank: Learning to Rerank Text with Compressed Visual Tokens
RenderRank reranks documents from compressed visual tokens, using 16.5-35.5% fewer tokens and beating sub-4B text baselines.
Stories per day · 30 days
1 RSS
2 stories, newest first · one card per story
Stories tagged #beir
Linkup Research Releases SPARSEUP: A 149M-Parameter Open-Source Sparse Embedding Model
Linkup Research released SPARSEUP, a 149M-parameter open-source sparse embedding model under Apache 2.0, scoring 56.4 nDCG@10 on BEIR-13.