RenderRank reranks documents as images: 35% fewer tokens, beats sub-4B text rerankers

nlpai-lab · hf · 2026-09-29

nlpai-lab introduces RenderRank, a reranker that renders documents as images and scores relevance from compressed visual tokens instead of text sequences. Training first aligns visual relevance scores with a text-based teacher, then refines relative positive/negative scores.

Results show compressed visual representations are a viable alternative to text tokens for document reranking.

Original post →

More from Research

Research channel →