miniReranker reduces multimodal reranking runtime to under 1% of the dense baseline under high-reuse conditions while retaining over 96% of performance via vision-first prompting, early exit, sparse cross-segment attention, and embedder-guided token pruning.
Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.IR 2years
2026 2representative citing papers
RouteHead trains a lightweight router to dynamically select optimal LLM attention heads per query for improved attention-based document re-ranking.
citing papers explorer
-
miniReranker: Efficient Multimodal Reranking through Visual Cache Reuse and Interaction Sparsity
miniReranker reduces multimodal reranking runtime to under 1% of the dense baseline under high-reuse conditions while retaining over 96% of performance via vision-first prompting, early exit, sparse cross-segment attention, and embedder-guided token pruning.
-
Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models
RouteHead trains a lightweight router to dynamically select optimal LLM attention heads per query for improved attention-based document re-ranking.