# MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing

Source: [MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing](<https://www.sota2.com/research/paper/6926898dd6b0dd33429303a8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-27T05:02:27.865Z

Authors: Changho Choi, Minho Kim, Jinkyu Kim

Published: 2025-11-25T06:18:18.000Z

## Abstract

Despite decades of progress, a truly input-size agnostic visual encoder-a fundamental characteristic of human vision-has remained elusive. We address this limitation by proposing \\textbf{MambaEye}, a novel, causal sequential encoder that leverages the low complexity and causal-process based pure Mamba2 backbone. Unlike previous Mamba-based vision encoders that often employ bidirectional processing, our strictly unidirectional approach preserves the inherent causality of State Space Models, enabling the model to generate a prediction at any point in its input sequence. A core innovation is our use of relative move embedding, which encodes the spatial shift between consecutive patches, providing a strong inductive bias for translation invariance and making the model inherently adaptable to arbitrary image resolutions and scanning patterns. To achieve this, we introduce a novel diffusion-inspired loss function that provides dense, step-wise supervision, training the model to build confidence as it gathers more visual evidence. We demonstrate that MambaEye exhibits robust performance across a wide range of image resolutions, especially at higher resolutions such as $1536^2$ on the ImageNet-1K classification task. This feat is achieved while maintaining linear time and memory complexity relative to the number of patches.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.19963>)

[PDF](<https://arxiv.org/pdf/2511.19963.pdf>)
