reranking

RenderRank: Learning to Rerank Text with Compressed Visual Tokensarxiv.org

RenderRank renders documents as images and uses a vision‑language model to produce compressed visual tokens for reranking, cutting input length by up to 35% while achieving higher NDCG@10 than text‑only baselines. It shows especially strong gains on long‑document datasets with half the token count and 1.7× throughput.