# Why VLMs Miss Small Objects, and When Zooming In Is Safe

arXiv: https://arxiv.org/abs/2610.09313 · HTML: https://mlsanity.com/paper/2610.09313/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 11 of its 49 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)

## Builds on (most cited first, 11 of 11)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V](https://mlsanity.com/paper/2310.11441/) (2023)
- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://mlsanity.com/paper/2506.23918/) (2025)
- [ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration](https://mlsanity.com/paper/2411.16044/) (2024)
- [Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs](https://mlsanity.com/paper/2505.15436/) (2025)
- [CountQA: How Well Do MLLMs Count in the Wild?](https://mlsanity.com/paper/2508.06585/) (2025)
- [HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling](https://mlsanity.com/paper/2510.00054/) (2025)
- [Visual Structures Helps Visual Reasoning: Addressing the Binding Problem in VLMs](https://mlsanity.com/paper/2506.22146/) (2025)
- [AECV-Bench: Benchmarking Multimodal Models on Architectural and Engineering Drawings Understanding](https://mlsanity.com/paper/2601.04819/) (2026)
- [ArchCAD-400K: A Large-Scale CAD drawings Dataset and New Baseline for Panoptic Symbol Spotting](https://mlsanity.com/paper/2503.22346/) (2025)
- [DrawingVQA: A Real-World Benchmark for Multi-Depth Visual-Textual Reasoning on Construction Drawings](https://mlsanity.com/paper/2607.15418/) (2026)

## Abstract (arXiv)

Vision-language models (VLMs) often miss small objects in large images. We ask three questions: what limits them, which of these limits better models can remove, and whether the classical way of handling large images, local decomposition, still has a future. We answer them with a theory built on two quantities of the image interface: S, the number of visual tokens across an object's side, and L, the content a call must cover. The limits: a W x H image sent whole within N tokens gives an object of side m at most m*sqrt(N/(WH)) tokens per side. Doubling the token budget N therefore raises the largest S a whole image can reach by only 41%, and seeing an image at the S an object needs costs at least order S^2 tokens whatever the model. If recognition improves gradually with S, any search strategy, zoom agents included, obeys a recall-cost frontier. What better models can change: the S an object needs and how much one call can carry, measured in bits per object found; the coverage cost remains. Decomposition: yes. Assuming only that more tokens per object and less content per call do not hurt on average, splitting an image cannot lower recall if no view zooms out relative to the whole image and views overlap by one object. Neither part of this condition can be dropped; we bound the cost of every such decomposition, and a simple rule approaches the bound as the image grows. We test the theory in about 177,000 requests on 797 images. On controlled images, none of 40 orderings predicted for 8 VLMs is violated. Checked after the fact on drawings, floor plans, natural and synthetic images, 61 of 89 implied orderings hold significantly and 4 fail, all for OpenAI models given more pixels than their default path. On construction drawings the rule never significantly lowered recall relative to the whole image and raised it by up to 0.28. Code and data: https://github.com/shijunzhe/vlm-small-objects