# Zoomer: Adaptive Image Focus Optimization for Black-box MLLM

arXiv: https://arxiv.org/abs/2505.00742 · HTML: https://mlsanity.com/paper/2505.00742/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 30 of its 32 references that are in the map.
- First posted on arXiv 30 Apr 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 30 of 30)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning](https://mlsanity.com/paper/2310.09478/) (2023)
- [LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models](https://mlsanity.com/paper/2407.07895/) (2024)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs](https://mlsanity.com/paper/2312.14135/) (2023)
- [LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images](https://mlsanity.com/paper/2403.11703/) (2024)
- [DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection](https://mlsanity.com/paper/2209.09407/) (2022)
- [AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models](https://mlsanity.com/paper/2308.15366/) (2023)
- [Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models](https://mlsanity.com/paper/2408.15556/) (2024)
- [Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models](https://mlsanity.com/paper/2403.03003/) (2024)
- [Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models](https://mlsanity.com/paper/2406.08487/) (2024)
- [Many-Shot In-Context Learning in Multimodal Foundation Models](https://mlsanity.com/paper/2405.09798/) (2024)
- [EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model](https://mlsanity.com/paper/2406.20076/) (2024)
- [EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension](https://mlsanity.com/paper/2311.15879/) (2023)
- [Attentive Mask CLIP](https://mlsanity.com/paper/2212.08653/) (2022)
- [MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning](https://mlsanity.com/paper/2406.17770/) (2024)

## Built on by (most cited first, 6 of 6)

- [Zoom-Refine: Boosting High-Resolution Multimodal Understanding via Localized Zoom and Self-Refinement](https://mlsanity.com/paper/2506.01663/) (2025)
- [DeepScan: A Training-Free Framework for Visually Grounded Reasoning in Large Vision-Language Models](https://mlsanity.com/paper/2603.03857/) (2026)
- [PointVG-R: Internalizing Geometric Reasoning in MLLMs for Precise Pointing Localization via Visual Chain of Thought](https://mlsanity.com/paper/2606.24539/) (2026)
- [LLM Code Smells: A Taxonomy and Detection Approach](https://mlsanity.com/paper/2605.22976/) (2026)
- [ShotCrop3: Cropping Human-Centric Images into Cinematic Triple-Shot Compositions](https://mlsanity.com/paper/2606.05635/) (2026)
- [Dynamic Resolution Routing for Efficient Egocentric Grounding](https://mlsanity.com/paper/2608.01638/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) such as GPT-4o, Gemini Pro, and Claude 3.5 have enabled unified reasoning over text and visual inputs, yet they often hallucinate in real world scenarios especially when small objects or fine spatial context are involved. We pinpoint two core causes of this failure: the absence of region-adaptive attention and inflexible token budgets that force uniform downsampling, leading to critical information loss. To overcome these limitations, we introduce Zoomer, a visual prompting framework that delivers token-efficient, detail-preserving image representations for black-box MLLMs. Zoomer integrates (1) a prompt-aware emphasis module to highlight semantically relevant regions, (2) a spatial-preserving orchestration schema to maintain object relationships, and (3) a budget-aware strategy to adaptively allocate tokens between global context and local details. Extensive experiments on nine benchmarks and three commercial MLLMs demonstrate that Zoomer boosts accuracy by up to 27% while cutting image token usage by up to 67%. Our approach establishes a principled methodology for robust, resource-aware multimodal understanding in settings where model internals are inaccessible.