# MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs

arXiv: https://arxiv.org/abs/2502.17422 · HTML: https://mlsanity.com/paper/2502.17422/

## Key facts

- Cited by 176 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 52 of its 59 references that are in the map.
- First posted on arXiv 24 Feb 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 52)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks](https://mlsanity.com/paper/2208.10442/) (2022)
- [V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs](https://mlsanity.com/paper/2312.14135/) (2023)

## Built on by (most cited first, 30 of 176)

- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://mlsanity.com/paper/2506.23918/) (2025)
- [Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation](https://mlsanity.com/paper/2605.18740/) (2026)
- [Vision Language Models are Biased](https://mlsanity.com/paper/2505.23941/) (2025)
- [Look-Back: Implicit Visual Re-focusing in MLLM Reasoning](https://mlsanity.com/paper/2507.03019/) (2025)
- [Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception](https://mlsanity.com/paper/2602.11858/) (2026)
- [Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2505.20272/) (2025)
- [Backdoor Cleaning without External Guidance in MLLM Fine-tuning](https://mlsanity.com/paper/2505.16916/) (2025)
- [Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture](https://mlsanity.com/paper/2509.02359/) (2025)
- [Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning](https://mlsanity.com/paper/2510.12712/) (2025)
- [ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness](https://mlsanity.com/paper/2504.10514/) (2025)
- [Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipes](https://mlsanity.com/paper/2504.15037/) (2025)
- [FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering](https://mlsanity.com/paper/2506.21710/) (2025)
- [HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation](https://mlsanity.com/paper/2505.11454/) (2025)
- [A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models](https://mlsanity.com/paper/2508.01548/) (2025)
- [SATORI-R1: Incentivizing Multimodal Reasoning through Explicit Visual Anchoring](https://mlsanity.com/paper/2505.19094/) (2025)
- [HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling](https://mlsanity.com/paper/2510.00054/) (2025)
- [True Multimodal In-Context Learning Needs Attention to the Visual Context](https://mlsanity.com/paper/2507.15807/) (2025)
- [Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation](https://mlsanity.com/paper/2509.22496/) (2025)
- [Thinking with Visual Abstract: Enhancing Multimodal Reasoning via Visual Abstraction](https://mlsanity.com/paper/2505.20164/) (2025)
- [See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model](https://mlsanity.com/paper/2509.16087/) (2025)
- [MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs](https://mlsanity.com/paper/2511.14159/) (2025)
- [Thinking in 360deg: Humanoid Visual Search in the Wild](https://mlsanity.com/paper/2511.20351/) (2025)
- [CROP: Contextual Region-Oriented Visual Token Pruning](https://mlsanity.com/paper/2505.21233/) (2025)
- [Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping](https://mlsanity.com/paper/2510.09741/) (2025)
- [Agentic Learner with Grow-and-Refine Multimodal Semantic Memory](https://mlsanity.com/paper/2511.21678/) (2025)
- [Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning](https://mlsanity.com/paper/2506.07227/) (2025)
- [Through the Magnifying Glass: Adaptive Perception Magnification for Hallucination-Free VLM Decoding](https://mlsanity.com/paper/2503.10183/) (2025)
- [NeSyGeo: A Neuro-Symbolic Framework for Multimodal Geometric Reasoning Data Generation](https://mlsanity.com/paper/2505.17121/) (2025)
- [DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning](https://mlsanity.com/paper/2509.20912/) (2025)
- [LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models](https://mlsanity.com/paper/2505.15616/) (2025)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) have experienced rapid progress in visual recognition tasks in recent years. Given their potential integration into many critical applications, it is important to understand the limitations of their visual perception. In this work, we study whether MLLMs can perceive small visual details as effectively as large ones when answering questions about images. We observe that their performance is very sensitive to the size of the visual subject of the question, and further show that this effect is in fact causal by conducting an intervention study. Next, we study the attention patterns of MLLMs when answering visual questions, and intriguingly find that they consistently know where to look, even when they provide the wrong answer. Based on these findings, we then propose training-free visual intervention methods that leverage the internal knowledge of any MLLM itself, in the form of attention and gradient maps, to enhance its perception of small visual details. We evaluate our proposed methods on two widely-used MLLMs and seven visual question answering benchmarks and show that they can significantly improve MLLMs' accuracy without requiring any training. Our results elucidate the risk of applying MLLMs to visual recognition tasks concerning small details and indicate that visual intervention using the model's internal state is a promising direction to mitigate this risk.