Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception

• URL: http://arxiv.org/abs/2602.11858v2
• Date: Mon, 16 Feb 2026 11:54:52 GMT
• Title: Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
• Authors: Lai Wei, Liangbo He, Jun Lan, Lingzhong Dong, Yutong Cai, Siyuan Li, Huijia Zhu, Weiqiang Wang, Linghe Kong, Yue Wang, Zhuosheng Zhang, Weiran Huang,
• Abstract summary: Region-to-Image Distillation transforms zooming from an inference-time tool into a training-time primitive.<n>We show that our models achieve leading performance across multiple fine-grained perception benchmarks.
• Score: 43.08943307183693
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Large Language Models (MLLMs) excel at broad visual understanding but still struggle with fine-grained perception, where decisive evidence is small and easily overwhelmed by global context. Recent "Thinking-with-Images" methods alleviate this by iteratively zooming in and out regions of interest during inference, but incur high latency due to repeated tool calls and visual re-encoding. To address this, we propose Region-to-Image Distillation, which transforms zooming from an inference-time tool into a training-time primitive, thereby internalizing the benefits of agentic zooming into a single forward pass of an MLLM. In particular, we first zoom in to micro-cropped regions to let strong teacher models generate high-quality VQA data, and then distill this region-grounded supervision back to the full image. After training on such data, the smaller student model improves "single-glance" fine-grained perception without tool use. To rigorously evaluate this capability, we further present ZoomBench, a hybrid-annotated benchmark of 845 VQA data spanning six fine-grained perceptual dimensions, together with a dual-view protocol that quantifies the global--regional "zooming gap". Experiments show that our models achieve leading performance across multiple fine-grained perception benchmarks, and also improve general multimodal cognition on benchmarks such as visual reasoning and GUI agents. We further discuss when "Thinking-with-Images" is necessary versus when its gains can be distilled into a single forward pass. Our code is available at https://github.com/inclusionAI/Zooming-without-Zooming.

Related papers

• GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagery [69.05066425853326]
  "thinking-with-images" paradigm enables multimodal large language models (MLLMs) to actively explore visual scenes via zoom-in tools.<n>This is essential for ultra-high-resolution (UHR) remote sensing VQA, where task-relevant cues are sparse and tiny.<n>We propose GeoEyes, a training framework consisting of (1) a cold-start SFT dataset, UHR Chain-of-Zoom (UHR-CoZ), which covers diverse zooming regimes, and (2) an agentic reinforcement learning method, AdaZoom-GRPO, that explicitly rewards evidence gain and answer improvement during zoom
  arXiv  Detail & Related papers  (2026-02-15T15:50:55Z)
• Training Multi-Image Vision Agents via End2End Reinforcement Learning [51.81337984526068]
  We propose IMAgent, an open-source vision agent trained via end-to-end reinforcement learning.<n>By leveraging a multi-agent system, we generate challenging and visually-rich multi-image QA pairs.<n>We develop two specialized tools for visual reflection and confirmation, allowing the model to proactively reallocate its attention to image content.
  arXiv  Detail & Related papers  (2025-12-05T10:02:38Z)
• LGCA: Enhancing Semantic Representation via Progressive Expansion [0.0]
  Localized-Globalized Cross-Alignment (LGCA) is a framework that first captures the local features of an image and then repeatedly selects the most salient regions and expands them.<n>Our method substantially improves zero-shot performance across diverse datasets, outperforming state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-11-01T06:09:42Z)
• ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration [39.2654025469784]
  We propose Zoom Eye, a training-free, model-agnostic tree search algorithm tailored for vision-level reasoning.<n>The algorithm enables MLLMs to simulate human-like zooming behavior by navigating from root to leaf nodes in search of task-relevant visual evidence.
  arXiv  Detail & Related papers  (2024-11-25T02:15:30Z)
• Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models [44.437693135170576]
  We propose a new framework, LMM with Sophisticated Tasks, Local image compression, and Mixture of global Experts (SliME) We extract contextual information from the global view using a mixture of adapters, based on the observation that different adapters excel at different tasks. The proposed method achieves leading performance across various benchmarks with only 2 million training data.
  arXiv  Detail & Related papers  (2024-06-12T17:59:49Z)
• Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs [49.88461345825586]
  This paper proposes a new framework to enhance the fine-grained image understanding abilities of MLLMs. We present a new method for constructing the instruction tuning dataset at a low cost by leveraging annotations in existing datasets. We show that our model exhibits a 5.2% accuracy improvement over Qwen-VL and surpasses the accuracy of Kosmos-2 by 24.7%.
  arXiv  Detail & Related papers  (2023-10-01T05:53:15Z)
• Extending global-local view alignment for self-supervised learning with remote sensing imagery [1.5192294544599656]
  Self-supervised models acquire general feature representations by formulating a pretext task that generates pseudo-labels for massive unlabeled data. Inspired by DINO, we formulate two pretext tasks for self-supervised learning on remote sensing imagery (SSLRS) We extend DINO and propose DINO-MC which uses local views of various sized crops instead of a single fixed size.
  arXiv  Detail & Related papers  (2023-03-12T14:24:10Z)
• USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval [115.28586222748478]
  Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality. Existing approaches typically suffer from two major limitations.
  arXiv  Detail & Related papers  (2023-01-17T12:42:58Z)
• MAF: Multimodal Alignment Framework for Weakly-Supervised Phrase Grounding [74.33171794972688]
  We present algorithms to model phrase-object relevance by leveraging fine-grained visual representations and visually-aware language representations. Experiments conducted on the widely-adopted Flickr30k dataset show a significant improvement over existing weakly-supervised methods.
  arXiv  Detail & Related papers  (2020-10-12T00:43:52Z)

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.