{"ID":2836942,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.20265","arxiv_id":"2511.20265","title":"Segment-Wise Flow Matching for Vision-Aided mmWave V2I Beam Prediction","abstract":"This paper proposes a vision-conditioned flow matching (FM) framework for beam prediction in millimeter-wave vehicle-to-infrastructure links. Instead of modeling discrete beam-index sequences, the proposed method learns the temporal evolution of normalized beam receive power vectors through a continuous vector field governed by an ordinary differential equation, enabling smooth dynamics and efficient sampling. By imposing FM over beam-state transitions and jointly optimizing beam prediction and flow consistency, the proposed framework provides a unified model for future beam prediction. Experimental results show that the proposed FM-based model significantly improves beam prediction performance over baselines, approaches the performance of large language model-based methods, and reduces predictor-side inference latency by about $6.9\\times$ on GPU and $2.8\\times10^3\\times$ on CPU, respectively.","short_abstract":"This paper proposes a vision-conditioned flow matching (FM) framework for beam prediction in millimeter-wave vehicle-to-infrastructure links. Instead of modeling discrete beam-index sequences, the proposed method learns the temporal evolution of normalized beam receive power vectors through a continuous vector field go...","url_abs":"https://arxiv.org/abs/2511.20265","url_pdf":"https://arxiv.org/pdf/2511.20265v2","authors":"[\"Can Zheng\",\"Jiguang He\",\"Chung G. Kang\",\"Guofa Cai\",\"Chongwen Huang\",\"Henk Wymeersch\"]","published":"2025-11-25T12:50:11Z","proceeding":"eess.SP","tasks":"[\"eess.SP\"]","methods":"[\"Language Model\"]","has_code":false}