←Back to NewsAI News/ImagerepoImageOpen SourceRelateAnything Maps Object Relationships 7.8x Faster Than Rival SystemsA 53M-parameter open-vocabulary scene-graph model runs at 20ms per frame, understands 19,103 relation phrases, and needs no object labels.SourceAlphaSignalPublishedSep 23, 2026, 5:18 AMAuthorAlphaSignal NewsroomRead1 min readA 53M-parameter open-vocabulary scene-graph model runs at 20ms per frame, understands 19,103 relation phrases, and needs no object labels.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsArtificial Analysis · newsAnt Group's Ming-Image Tops Open-Weight UI Design Rankings Among 81 ModelsQwen · newsAlibaba's Qwen-Image-2.1 Ships Transparent Image Generation Without Extra ToolsJina AI · newsJina AI's jina-ocr-v1 Parses PDF Pages at 2.57 Pages per Second
