SOURCE-LINKED INTELLIGENCE

LiAuto-MindViT: A Hybrid Vision Backbone with Adaptive Bidirectional Mamba

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

While Mamba-based models have shown strong potential for long sequence modeling, adapting them to vision is challenging due to the requirement of local neighborhood correlations and multi-directional spatial contexts for visual understanding. In this paper, we present LiAuto-MindViT, a novel hybrid vision backbone that synergizes the strengths of CNNs, Mamba, and Transformers. The core of our design is the Adaptive Bidirectional Mamba (ABM), which eliminates the directional bias of unidirectional SSMs through bidirectional selective scanning with learnable alpha blending, enabling content-adap

Read original source ↗ Open in workspace

recordType

paper

region

Global