{"ID":2836763,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.19963","arxiv_id":"2511.19963","title":"MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing","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.","short_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...","url_abs":"https://arxiv.org/abs/2511.19963","url_pdf":"https://arxiv.org/pdf/2511.19963v1","authors":"[\"Changho Choi\",\"Minho Kim\",\"Jinkyu Kim\"]","published":"2025-11-25T06:18:18Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Diffusion Model\"]","has_code":false}