# Why We Look Where We Look: Emergent Human-like Fixations of a Foveated Visual Language Model Maximizing Scene Understanding

arXiv: https://arxiv.org/abs/2605.17823 · HTML: https://mlsanity.com/paper/2605.17823/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 10 of its 71 references that are in the map.
- First posted on arXiv 18 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 10 of 10)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Ovis: Structural Embedding Alignment for Multimodal Large Language Model](https://mlsanity.com/paper/2405.20797/) (2024)
- [Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding](https://mlsanity.com/paper/2601.10611/) (2026)
- [Jasper and Stella: distillation of SOTA embedding models](https://mlsanity.com/paper/2412.19048/) (2024)
- [Ovis2.5 Technical Report](https://mlsanity.com/paper/2508.11737/) (2025)
- [The Limits of Learning from Pictures and Text: Vision-Language Models and Embodied Scene Understanding](https://mlsanity.com/paper/2603.26589/) (2026)

## Abstract (arXiv)

When humans view scenes without a specific task (free-viewing), they initially direct their eye movements toward the scene center and then fixate on people, text, objects being gazed at or grasped, and semantically meaningful regions. What these signature fixation patterns reflect and whether they optimize an underlying perceptual task remain unknown. We show that a computational agent with simulated foveation, trained to optimize scene comprehension, exhibits emergent human fixation signature patterns. In contrast, versions of the agent trained to search or classify scenes, or equipped with peripheral vision that was better or worse than human vision, predicted human fixation patterns less accurately. Thus, human free-viewing fixation patterns may emerge as a functional byproduct of optimizing scene comprehension under the biological constraints of foveated vision.