cs.CVNov 11, 2026

Keep Images in Sight: Visual Position Re-Anchoring for Long-Context MLLMs

Authors: Juntao Xu, Qichai Zhao, Rui Sun, Zhouyang Jiang, Shiwei Wu, Zhi Li, Kaisheng Ma, Yu Liu

Organizations: Tsinghua University

Abstract

Long-context multimodal intelligence requires revisiting earlier images as conversations and documents accumulate, yet retaining an image does not guarantee reliable access to its details. By varying context length, redistributing a fixed text passage around the image, and changing positions without adding text, we identify the positional relation between images and questions as a direct influence on visual access. To address this gap, we propose Visual Position Re-Anchoring (VPR), a training-free method that shifts cached visual-key rotary phases toward a short-context reference before question processing. It operates directly on the existing KV cache, preserving standard attention computation without extracting attention maps or adding model forward passes. We develop static and continuous compensation schedules, using the static schedule by default. Across ten checkpoints and ten benchmarks, static VPR improves 97 of 100 model--task scores. Further analysis shows greater attention to regions containing answer evidence across six checkpoints, with minimal runtime overhead under fixed rotary frequencies. These findings demonstrate an efficient way to sustain visual access through positional adjustment within the cache.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Jun 25, 2026

Adaptive Visual KV Cache Reuse for Efficient Multi-Turn Iterative Multimodal Reasoning

Multi-turn visual reasoning acquires evidence through repeated cropping and local inspection, but overlapping observations lead to redundant visual encoding and prefill. We propose an adaptive visual KV cache reuse framework that reduces repeated processing while retaining access to additional image detail. The central difficulty is that skipping visual prefill also removes the interaction between a new observation and the current reasoning: historical keys remain bound to old positions, while historical values have not incorporated the intent formed between crops. Our framework first selects full re-encoding or regional reuse according to crop size and cache availability. On the reuse path, Positional Key Rebinding (PKR) corrects attention matching at the new positions, and Intent-guided Value Enhancement (IVE) uses pre-crop reasoning attention to strengthen content relevant to the current objective. Source states from fully re-encoded crops are retained for subsequent retrieval and reuse. The framework requires no additional training on reuse hits, it bypasses the visual encoder and prefill for the selected visual tokens, then resumes normal text reasoning. Experiments show that our method reduces inference time while preserving the overall accuracy of multi-turn visual reasoning that relies on intermediate crop images.
Aug 25, 2026

VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference

While Vision Large Language Models (VLLMs) have achieved remarkable success in multimodal reasoning, their long-context inference remains prohibitively expensive due to the massive computation and memory overhead of visual Key-Value (KV) caches. Existing KV compression methods often apply uniform pruning across visual tokens and layers, leading to substantial information loss and degraded performance.To address this challenge, we propose VisCache, a plug-and-play framework for coarse-to-fine Visual KV Cache pruning without training, which consists of two synergistic stages. First, a lightweight VLM filters temporal redundancy by selectively forwarding semantically informative keyframes. Second, we introduce {PruneKV}, a surgical KV compression algorithm tailored to the attention dynamics of VLLMs. Unlike rigid pruning strategies, PruneKV adopts a parabolic layer-wise budget allocation together with an asymmetric update mechanism that selectively prunes keys while fusing values, thereby preserving critical contextual information. Extensive experiments demonstrate that VisCache substantially improves inference efficiency, achieving up to {2.35×\times speedup} and significant memory reduction while maintaining competitive performance with only {19--28%} KV cache retention. VisCache consistently outperforms existing baselines, establishing a new Pareto frontier between efficiency and performance for long-context VLLM inference. Code is available at https://github.com/Wlklk/VisCache
Jul 30, 2026

ReToken: Improving Long-Context VLMs with Visual Retrieval Token

Long visual contexts challenge vision-language models: performance degrades as the number of distractors grows, and processing all tokens at once can exceed GPU memory limits. We present RETOKEN, a single learnable embedding that extracts retrieval signals from the VLM's internal representations to select query-relevant visual tokens from the pre-filled KV cache. This enables retrieval within the answering VLM, without a separate retriever or re-encoding. Despite being trained on only a small image-QA dataset, RETOKEN generalizes across image and video benchmarks. On Visual Haystacks, it improves Qwen3VL-8B by 13.4 points and InternVL3.5 by 12.4 points (>20% relative). On LVBench, it transfers zero-shot to long video and improves Qwen3VL-8B by 8.0 points. Thanks to its lightweight design, both training and long-video inference fit on a single H100. Code is available at: https://github.com/avaxiao/ReToken