QV-PIC: Query-Aware Visual Position-Independent Caching for Efficient RAG Serving
On the map: Retrieval-augmented generation → Generation and context integration
Abstract (arXiv)
Retrieval-Augmented Generation (RAG) repeatedly prefills identical text chunks across queries, incurring redundant computations. Position-Independent Caching (PIC) mitigates it by reusing precomputed Key-Value (KV) across positions, but its efficiency is constrained by the large volume of text tokens. Rendering text chunks as images can compress the text into fewer visual tokens, but the rendered-image PIC suffers more severe quality degradation than the text PIC. This representation-specific gap primarily arises from contextual mismatches across independently compiled caches and the loss of fine-grained textual evidence during visual compression. Existing PIC repair methods mainly address the former through selective recomputation, but they incur online computation and cannot recover lost textual details. We propose QV-PIC, a query-aware dual-resolution PIC reuse framework guided by model-native templates. Offline, QV-PIC compiles visual caches under the model's native chat-template prefix, improving PIC quality without online recomputation. Online, it preserves global context with low resolution and restores fine-grained textual evidence within a high-resolution budget by cumulative query relevance scores, retaining the efficiency benefit of visual compression. Across six tasks, QV-PIC improves average F1 by 21.6 points over vanilla rendered-image PIC, closes the gap to vanilla text PIC, and surpasses optimized text PIC by 2.58 F1 while reducing TTFT by 17.2%. Relative to full prefill, it cuts TTFT by 83.8%.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 7 of its 10 references that are in the map. First posted on arXiv 12 Aug 2026.
Builds on
7 of 10 references.
References · 7
- 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
- 2023Prompt Cache: Modular Attention Reuse for Low-Latency Inferencecited by 268
- 2026DeepSeek-OCR 2: Visual Causal Flowcited by 74
- 2026LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligencecited by 39
- 2025MPIC: Position-Independent Multimodal Context Caching System for Efficient MLLM Servingcited by 8
- 2025VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inferencecited by 7
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving
- 2026RAGOCR: Optical Compression of Retrieval-Augmented Text via Visual Representation
- 2025Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries
- 2026RelaxKV: Recomputation Guided by the Query with Sparse Context Attention for Efficient KV Cache Reuse
- 2026ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation
- 2026KIRA: Knowledge-Intensive Image Retrieval and Reasoning Architecture for Specialized Visual Domains
- 2026ATTUNER: Recomputation-Free KV Cache Reuse via Query-Side Adaptation
- 2024EPIC: Efficient Position-Independent Caching for Serving Large Language Models