cs.CVNov 18, 2026

R3^{3}Sieve: Suppressing Unconditional Information from Attention to Answers for High-Resolution VQA

Authors: Yifan Cao, Yawen Zhang, Xiaocui Yang, Faxian Wan, Shi Feng, Daling Wang, Yifei Zhang, Shangshu Yu, 

Organizations: School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China · School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University, Shanghai 201210, China · Jiangnan University, Wuxi, China

Abstract

High-resolution visual question answering (VQA) requires models to identify question-relevant small objects in high-resolution images and select the correct answer based on what they recognize, demanding fine-grained perception. Previous methods focus on obtaining better visual evidence (image crops), but obtaining it alone is insufficient, using it effectively is equally crucial. Visual evidence should therefore be utilized as effectively as possible throughout inference. We argue that small-target evidence is obscured by unconditional information that remains observable in subsequent processing even after the condition on which it should depend is removed. Such information hinders the effective use of small-target evidence. We propose R3^{3}Sieve (Residual-Region-Response Sieve), a training-free framework. We divide inference into three stages---localization, cropping, and answering---and introduce distinct counterfactual references to suppress interference at each stage. During localization, the Shared-Subspace Canceller (SSC) uses a generic image description to construct a counterfactual reference and obtain question-relevant attention maps. During cropping, the Unique-Contribution Spotter (UCS) constructs counterfactual references from visual and non-visual features to identify distinctive, complementary crop regions. During answering, the Content-Aligned Voter (CAV) constructs an image-free branch to calibrate answer responses. Experiments on three high-resolution VQA benchmarks show that R3^{3}Sieve achieves the highest overall accuracy among compared methods across diverse settings, improving base models by up to 21.5 percentage points.

Figures & tables

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Jul 30, 2026

Thinking Once Is Enough: Intermediate-Layer Evidence Routing for High-Resolution VQA

High-resolution visual question answering (HR-VQA) is often treated as a problem of insufficient evidence acquisition, where failing multimodal large language models must inspect images again through cropping, re-encoding, or multi-round search. We show that this view is incomplete: in many cases, fine-grained evidence has already survived visual encoding and become identifiable and influential within an intermediate-layer routing window, but is later diluted before answer generation. We propose Thinking-Once, a training-free, single-visual-pass evidence-routing method that reconstructs question-conditioned attention at this window, preserves core entity tokens and compact background context, and routes this evidence to later layers without extra visual encoding. Across five base models, Thinking-Once consistently improves or matches the corresponding base setting, increasing the average scores on V∗^*Bench, HRBench-4K, and HRBench-8K by +3.1, +3.0, and +2.7 points while reducing the average peak memory by about 4,GB. On Qwen2.5-VL-7B, it improves the three benchmarks by +9.9, +4.6, and +5.5 points, raising the cross-benchmark mean from 72.5 to 79.1. With the ZwZ-8B base model, Thinking-Once reaches a mean score of 82.7. Against 11 open-source HR-VQA baselines, it obtains the best or tied-best score on all three benchmark averages and the best overall mean; for example, compared with DeepScan, it reduces V∗^*Bench inference time by 97.2% while improving the cross-benchmark mean from 77.8 to 79.1. These results show that HR-VQA can be improved by routing already encoded evidence rather than repeatedly acquiring new visual inputs. Code is available in the appendix.
Jan 25, 2026

R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation

Vision-centric retrieval for VQA requires retrieving images to supply missing visual cues and integrating them into the reasoning process. However, selecting the right images and integrating them effectively into the model's reasoning remains challenging. To address this challenge, we propose R3G, a modular Reasoning-Retrieval-Reranking framework. It first produces a brief reasoning plan that specifies the required visual cues, then adopts a two-stage strategy, with coarse retrieval followed by fine-grained reranking, to select evidence images. On MRAG-Bench, R3G improves accuracy across six MLLM backbones and nine sub-scenarios, achieving state-of-the-art overall performance. Ablations show that sufficiency-aware reranking and reasoning steps are complementary, helping the model both choose the right images and use them well. We release code and data at https://github.com/czh24/R3G.
Nov 18, 2026

SEE: Unlocking the Hidden Perception of Frozen VLMs

Vision-language models (VLMs) grasp the overall content of an image but often miss the fine details a question hinges on, such as a small object in a large photo or a number in a dense infographic. Yet even when their answer is wrong, the region they point to often contains the evidence. We introduce Self-Elicited Evidence (SEE), a training-free method that lets a frozen VLM look again where it points. When the initial answer has low confidence, SEE prompts the model to propose regions where the details may appear, answers the question on these enlarged crops, and aggregates the answers with the original prediction through confidence-weighted voting. The model also answers with its own transcript, which helps on text-rich images. SEE needs no detector or OCR engine. Across five backbones, SEE improves every small-object benchmark by 2.3-13.1 points and outperforms five training-free baselines on small objects. With SEE, Qwen3.5-4B surpasses the direct answer of Qwen3.5-9B and matches the 6 times larger Qwen3.5-27B.