miniReranker: Efficient Multimodal Reranking through Visual Cache Reuse and Interaction Sparsity

• URL: http://arxiv.org/abs/2606.10759v2
• Date: Tue, 16 Jun 2026 02:36:19 GMT
• Title: miniReranker: Efficient Multimodal Reranking through Visual Cache Reuse and Interaction Sparsity
• Abstract summary: Multimodal large language models (MLLMs) have recently shown strong potential as point-wise rerankers.<n>However, point-wise reranking suffers from substantial repeated computation across query--document pairs.<n>We propose a $textitvision-first$ formulation that improves both cache reuse efficiency and reranking performance.
• Score: 21.54829080388454
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal large language models (MLLMs) have recently shown strong potential as point-wise rerankers by directly modeling query--document relevance through next-token prediction. However, point-wise reranking suffers from substantial repeated computation across query--document pairs, while the causal structure of transformers allows only prefix segments to be reused via pre-caching. To address the misalignment of existing query-first and document-first formats with both VQA-style prompting and computation-aware reuse, we propose a $\textit{vision-first}$ formulation that improves both cache reuse efficiency and reranking performance. However, the remaining cost is still considerable and stems from three main sources: (1) $\textit{model depth}$, for which we reduce active parameters via early exit; (2) $\textit{cross-segment attention}$, which we restrict to a narrow interaction band across a few layers; and (3) $\textit{visual tokens}$, where we reduce the number of tokens via embedder-guided pruning. Together, these designs form miniReranker, which reduces reranking runtime to <1% of the dense implementation under high-reuse settings for a single query, while preserving >96% of the dense model performance.

Related papers

• CONDUIT: A Unified Residual-Stream Restoration Framework for KV Cache Reuse in Vision-Language Models [32.623898255947374]
  We propose CONDUIT, a training-free refresh policy that unifies single- and multi-image reuse as residual-stream restoration.<n>At a 10% refresh budget, CONDUIT 97.0-99.5% of the corresponding full-prefill five-dataset average across three VLM backbones and leads budgeted methods on average.
  arXiv  Detail & Related papers  (2026-09-05T02:34:16Z)
• Back from the Future: Key-Value Cache Management by Counter-Causal Surprise [67.1056509495879]
  Key-value (KV) cache management through compression and eviction strategies has emerged as an important research direction in recent years.<n>We propose a simple yet effective KV eviction scheme motivated by the insight that past tokens which can be well-predicted from more recent tokens are redundant.<n>We evaluate our strategy on various open-source LLMs and benchmark datasets showing competitive or improved performance over other state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-07-30T02:42:51Z)
• Sparse Prefix Caching for Hybrid and Recurrent LLM Serving [0.7284556903703034]
  We formalize sparse prefix caching as checkpoint placement under a distribution over overlap depths.<n>For use cases where requests share a non-trivial prefix, we show that our method consistently improves the frontier traced by standard asymmetry on real-world data.<n>It preserves exact outputs, does not change the recurrent computation itself or require new recurrent update kernels.
  arXiv  Detail & Related papers  (2026-04-17T09:24:58Z)
• Rethinking Token Reduction for Large Vision-Language Models [95.48478689025696]
  Large-Language Models (LVLMs) excel in visual understanding and reasoning, but the excessive visual tokens lead to high inference costs.<n>We propose a learning-based prompt-agnostic, termed MetaCompress, overcoming the limitations of generalization designs.
  arXiv  Detail & Related papers  (2026-03-23T08:40:08Z)
• Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution [52.76038908826961]
  We propose $textbfReMe$ ($textitRemember Me, Refine Me$) to bridge the gap between static storage and dynamic reasoning.<n>ReMe innovates across the memory lifecycle via three mechanisms: $textitmulti-faceted distillation$, which extracts fine-grained experiences.<n>Experiments on BFCL-V3 and AppWorld demonstrate that ReMe establishes a new state-of-the-art in agent memory system.
  arXiv  Detail & Related papers  (2025-12-11T14:40:01Z)
• $A^3$: Attention-Aware Accurate KV Cache Fusion for Fast Large Language Model Serving [42.02864241423696]
  Large language models (LLMs) have demonstrated strong capabilities in processing long contexts.<n>Despite their ability to handle long sequences, the resulting decoding latency and memory overhead remain substantial.<n>Recent advances in KV Cache reuse have shown potential to mitigate these costs, but still suffer from notable performance degradation.
  arXiv  Detail & Related papers  (2025-11-13T07:28:59Z)
• Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation [61.67090981767583]
  We introduce Mixture-of-Recursions (MoR), a unified framework that combines the two axes of efficiency inside a single Recursive Transformer.<n>MoR reuses a shared stack of layers across recursion steps to achieve parameter efficiency, while lightweight routers enable adaptive token-level thinking.<n>We also propose a KV sharing variant that reuses KV pairs from the first recursion, specifically designed to further decrease memory footprint.
  arXiv  Detail & Related papers  (2025-07-14T17:49:00Z)
• Plug-and-Play Context Feature Reuse for Efficient Masked Generation [36.563229330549284]
  Masked generative models (MGMs) have emerged as a powerful framework for image synthesis.<n>We introduce ReCAP (Reused Context-Aware Prediction), a plug-and-play module that accelerates inference in MGMs.
  arXiv  Detail & Related papers  (2025-05-25T10:57:35Z)
• Gumbel Reranking: Differentiable End-to-End Reranker Optimization [61.16471123356738]
  RAG systems rely on rerankers to identify relevant documents.<n> fine-tuning these models remains challenging due to the scarcity of annotated query-document pairs.<n>We propose Gumbel Reranking, an end-to-end training framework for rerankers aimed at minimizing the training-inference gap.
  arXiv  Detail & Related papers  (2025-02-16T13:23:39Z)
• EPIC: Efficient Position-Independent Caching for Serving Large Language Models [19.510078997414606]
  Caching improves serving performance by reusing Key-Value vectors across requests.<n>Existing context caching requires exact prefixes across requests.<n>We introduce Position-Independent Caching (PIC), which enables modular reuse of KV vectors regardless of prefixes.<n>We also introduce EPIC, a serving system incorporating our new LegoLink algorithm, which mitigates the inappropriate "attention sink" effect at every document beginning.
  arXiv  Detail & Related papers  (2024-10-20T08:42:29Z)
• Training-Free Exponential Context Extension via Cascading KV Cache [49.608367376911694]
  We introduce a novel mechanism that leverages cascading sub-cache buffers to selectively retain the most relevant tokens.<n>Our method reduces prefill stage latency by a factor of 6.8 when compared to flash attention on 1M tokens.
  arXiv  Detail & Related papers  (2024-06-24T03:59:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.