{"slug": "antennaflow-a-generative-flow-model-for-offset-correction-in-phaseless-antenna", "title": "AntennaFlow: A Generative Flow Model for Offset Correction in Phaseless Antenna Testing", "summary": "Researchers introduced AntennaFlow, a three-stage generative flow model that performs phaseless, offset-vector-free near-field to far-field reconstruction for large-aperture antenna testing, according to a paper published on arXiv as 2609.16948v1. AntennaFlow combines a contrastively learned offset-invariant encoder, deterministic flow-matching transport that maps offset amplitudes to center-aligned fields, and the Simplified Extrapolation Technique, whose Green-function Taylor expansion is valid only for centered fields. Experiments show the framework reconstructs from sparse amplitude-only measurements and consistently outperforms existing baselines while preserving physical consistency, addressing millimeter-wave phase acquisition costs and centering violations under offset mounting jointly rather than separately.", "body_md": "arXiv:2609.16948v1 Announce Type: new \nAbstract: Near-field to far-field transformation is central to large-aperture antenna testing, yet two coupled challenges remain: costly phase acquisition at millimeter-wave bands and violations of the centering assumption under offset mounting. Existing methods address these issues separately, requiring either dense full-field data or offset vectors. We tackle both jointly by exploiting a key observation: amplitude fields under different offsets are coordinate-transformed views of the same near field. The challenge is to recover the center-aligned field from offset amplitudes without a phase or offset vector. We propose AntennaFlow, a three-stage framework: a contrastively learned encoder that maps offset views to an offset-invariant embedding, a deterministic flow-matching transport that maps offset amplitudes to center-aligned ones, and the Simplified Extrapolation Technique, whose Green-function Taylor expansion is valid only for centered fields. Experiments show that AntennaFlow enables fast, phaseless, offset-vector-free NF--FF reconstruction from sparse amplitude-only measurements, consistently outperforming existing baselines while preserving physical consistency.", "url": "https://wpnews.pro/news/antennaflow-a-generative-flow-model-for-offset-correction-in-phaseless-antenna", "canonical_source": "https://www.machinebrief.com/news/antennaflow-a-generative-flow-model-for-offset-correction-in-rhlw", "published_at": "2026-09-16 04:00:00+00:00", "updated_at": "2026-09-16 05:36:11.365908+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "generative-ai"], "entities": ["AntennaFlow", "arXiv", "Simplified Extrapolation Technique"], "alternates": {"html": "https://wpnews.pro/news/antennaflow-a-generative-flow-model-for-offset-correction-in-phaseless-antenna", "markdown": "https://wpnews.pro/news/antennaflow-a-generative-flow-model-for-offset-correction-in-phaseless-antenna.md", "text": "https://wpnews.pro/news/antennaflow-a-generative-flow-model-for-offset-correction-in-phaseless-antenna.txt", "jsonld": "https://wpnews.pro/news/antennaflow-a-generative-flow-model-for-offset-correction-in-phaseless-antenna.jsonld"}}