{"ID":6620639,"CreatedAt":"2026-07-15T01:01:48.440468303Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.12681","arxiv_id":"2607.12681","title":"MambaPSA: A Mamba-based Replacement for C2PSA in YOLO26","abstract":"State space models (SSMs), notably Mamba, have recently emerged as efficient alternatives to self-attention with linear computational complexity. We investigate the integration of Mamba into YOLO26, the latest non-maximum suppression (NMS)-free object detection framework, by proposing MambaPSA, a lightweight Mamba-based replacement for the C2PSA block at the end of the backbone. To complement this study, we additionally insert a bidirectional Vision Mamba (BiViM) module at the P3, P4, and P5 levels of the neck. Experiments on PASCAL VOC 2007+2012 show that MambaPSA reduces parameters by 2.9%, FLOPs by 12.1%, and improves CPU inference throughput by 17.6% (from 17 to 20 FPS) with negligible accuracy change (-0.1 mAP50:95), while the P4 BiViM placement yields the best accuracy gain (+0.9 mAP50:95). These results suggest that SSMs offer a favorable efficiency-accuracy trade-off when replacing attention-based blocks in NMS-free lightweight detectors.","short_abstract":"State space models (SSMs), notably Mamba, have recently emerged as efficient alternatives to self-attention with linear computational complexity. We investigate the integration of Mamba into YOLO26, the latest non-maximum suppression (NMS)-free object detection framework, by proposing MambaPSA, a lightweight Mamba-base...","url_abs":"https://arxiv.org/abs/2607.12681","url_pdf":"https://arxiv.org/pdf/2607.12681v1","authors":"[\"Sheng-Wei Chan\",\"Chia-Min Lin\",\"Hsin-Jui Pan\",\"Ching-Yu Tsai\",\"Chih-Hsiang Yang\",\"Yung-Che Wang\",\"Jen-Shiun Chiang\"]","published":"2026-07-14T12:09:53Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}