# Loop to Look Better: Learning Adaptive Depth for Question-Guided Perception in Vision-Language Models

Authors: Wencheng Ye, Anning Hu, Hongye Fang, Tianyi Wang, Junchi Yan.

LoopLook repeatedly refines visual features in response to a question, with a learned stopping rule and token-wise mixing of intermediate states. Adapts the vision encoder while keeping the language model frozen; the extra computation occurs before ordinary answer generation.

First public: 2026-10-22.
ArXiv initial submission: 2026-10-22.

[Original paper](https://arxiv.org/abs/2610.30824) · [PDF](https://arxiv.org/pdf/2610.30824) · [HTML](https://arxiv.org/html/2610.30824v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.30824/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.30824/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.30824/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.30824/record.json)

## Approaches

- [Recurrent reasoning](https://latent-implicit-thinking.github.io/topics/recurrent-reasoning/): Repeat parts of the model or keep intermediate information in memory while working through a problem. Some methods also learn how many passes to run.

Reading-list version 0.11.0; literature checked through 2026-10-26.