{"id":83451,"topic":"ai","source":"Sohu","title":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一 - Sohu","url":"https://m.sohu.com/a/1076675399_115831?scm=10001.325_13-325_13.0.0-0-0-0-0.5_1334","url_hash":"e68908012925a9563db7e4529dd04a102c2cea55","author":"","summary":"<a href=\"https://news.google.com/rss/articles/CBMiiAFBVV95cUxNQl9XUTFYV1Fwa3RzdnJURGNqLVlsa1Ztdi00VFdlSkVINE1fMVBpdk9nY1N2TGVSRDFOUGhtcEJiSHhObXl6TlFRYTFYeUxmNnFWeDdoaWNSRWdER2FWY0RKUVZPRWtmeVJLTnZ6Zk9wV09zcHllQVY3dGxkR0s1b2xTa2o0dklJ?oc=5\" target=\"_blank\">vivo连发四款AI大模型 蓝心Nano 3B六项评测第一</a>&nbsp;&nbsp;<font color=\"#6f6f6f\">Sohu</font>","content":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一\n【CNMO科技消息】9月16日，在2026 vivo开发者大会上，vivo正式发布四款蓝心大模型，涵盖语音、端侧与云侧不同场景，进一步完善“以个人为中心的智能体大模型矩阵”。vivo表示，今年蓝心大模型将全面升级，核心目标是让系统拥有持续领先的“超强大脑”。\nvivo\n此次发布的四款模型分别是蓝心语音大模型、蓝心端侧大模型，以及蓝心云侧大模型Flash和Pro。其中，蓝心语音大模型采用全新端到端语音理解架构，融入更多个人化信息，在嘈杂环境下轻声说话、带口音、连续表达甚至中英混合，都能准确识别。\n蓝心端侧大模型（BlueLM-Nano 3B）主打实时感知与个人记忆沉淀。它能融合理解屏幕、图像、视频、文本和文件，不仅能看懂当下，还能记住用户的习惯偏好、用机状态、时空场景等。例如电话挂断后，系统可自动整理核心信息并生成记录。","image_url":"https://q0.itc.cn/q_70/images03/20260916/7bf39ea2451c4bcdbd1251811f5acc01.png","lang":"zh","published_at":"2026-09-16T02:29:00+00:00","fetched_at":"2026-09-16T03:15:08+00:00","status":"read","starred":0,"extract_state":"ok","summary_auto":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一\n【CNMO科技消息】9月16日，在2026…","cluster_id":null,"extract_retries":0,"extract_error":null,"contract_version":"news_item.v1","format_contract_version":"news_item_formats.v1","dedup_url":"https://m.sohu.com/a/1076675399_115831?scm=10001.325_13-325_13.0.0-0-0-0-0.5_1334","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 394 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":394,"summary_length":52,"usable_text_length":394,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":394,"summary_length":52}},"news_item":{"id":83451,"canonical_url":"https://m.sohu.com/a/1076675399_115831?scm=10001.325_13-325_13.0.0-0-0-0-0.5_1334","source_url":"https://m.sohu.com/a/1076675399_115831?scm=10001.325_13-325_13.0.0-0-0-0-0.5_1334","title":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一 - Sohu","source_name":"Sohu","author":null,"published_at":"2026-09-16T02:29:00+00:00","locale":"zh","topic":"ai","tags":[],"rss_summary":"<a href=\"https://news.google.com/rss/articles/CBMiiAFBVV95cUxNQl9XUTFYV1Fwa3RzdnJURGNqLVlsa1Ztdi00VFdlSkVINE1fMVBpdk9nY1N2TGVSRDFOUGhtcEJiSHhObXl6TlFRYTFYeUxmNnFWeDdoaWNSRWdER2FWY0RKUVZPRWtmeVJLTnZ6Zk9wV09zcHllQVY3dGxkR0s1b2xTa2o0dklJ?oc=5\" target=\"_blank\">vivo连发四款AI大模型 蓝心Nano 3B六项评测第一</a>&nbsp;&nbsp;<font color=\"#6f6f6f\">Sohu</font>","full_text":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一\n【CNMO科技消息】9月16日，在2026 vivo开发者大会上，vivo正式发布四款蓝心大模型，涵盖语音、端侧与云侧不同场景，进一步完善“以个人为中心的智能体大模型矩阵”。vivo表示，今年蓝心大模型将全面升级，核心目标是让系统拥有持续领先的“超强大脑”。\nvivo\n此次发布的四款模型分别是蓝心语音大模型、蓝心端侧大模型，以及蓝心云侧大模型Flash和Pro。其中，蓝心语音大模型采用全新端到端语音理解架构，融入更多个人化信息，在嘈杂环境下轻声说话、带口音、连续表达甚至中英混合，都能准确识别。\n蓝心端侧大模型（BlueLM-Nano 3B）主打实时感知与个人记忆沉淀。它能融合理解屏幕、图像、视频、文本和文件，不仅能看懂当下，还能记住用户的习惯偏好、用机状态、时空场景等。例如电话挂断后，系统可自动整理核心信息并生成记录。","excerpt":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一\n【CNMO科技消息】9月16日，在2026…","extraction":{"state":"ok","confidence":0.9,"error":null,"explanation":"High confidence: full text extraction produced 394 characters.","diagnostics_url":"/api/diagnose?url=https%3A//m.sohu.com/a/1076675399_115831%3Fscm%3D10001.325_13-325_13.0.0-0-0-0-0.5_1334","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 394 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":394,"summary_length":52,"usable_text_length":394,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":394,"summary_length":52}}},"display_formats":["compact","card","full","digest_section","json"]},"daily_stack_record":{"title":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一 - Sohu","url":"https://m.sohu.com/a/1076675399_115831?scm=10001.325_13-325_13.0.0-0-0-0-0.5_1334","summary":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一\n【CNMO科技消息】9月16日，在2026…","source":"Sohu","date":"2026-09-16T02:29:00+00:00","content":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一\n【CNMO科技消息】9月16日，在2026 vivo开发者大会上，vivo正式发布四款蓝心大模型，涵盖语音、端侧与云侧不同场景，进一步完善“以个人为中心的智能体大模型矩阵”。vivo表示，今年蓝心大模型将全面升级，核心目标是让系统拥有持续领先的“超强大脑”。\nvivo\n此次发布的四款模型分别是蓝心语音大模型、蓝心端侧大模型，以及蓝心云侧大模型Flash和Pro。其中，蓝心语音大模型采用全新端到端语音理解架构，融入更多个人化信息，在嘈杂环境下轻声说话、带口音、连续表达甚至中英混合，都能准确识别。\n蓝心端侧大模型（BlueLM-Nano 3B）主打实时感知与个人记忆沉淀。它能融合理解屏幕、图像、视频、文本和文件，不仅能看懂当下，还能记住用户的习惯偏好、用机状态、时空场景等。例如电话挂断后，系统可自动整理核心信息并生成记录。","confidence":0.9,"diagnostics_url":"/api/diagnose?url=https%3A//m.sohu.com/a/1076675399_115831%3Fscm%3D10001.325_13-325_13.0.0-0-0-0-0.5_1334","quality_bucket":"high","failure_kind":"none","retryable":false,"quality_reason":"High confidence: full text extraction produced 394 characters.","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 394 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":394,"summary_length":52,"usable_text_length":394,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":394,"summary_length":52}},"tags":[]},"fallback_formats":["markdown","json","html"],"actions":{"read":"/item/83451","export_markdown":"/api/items/83451/export?format=markdown","export_json":"/api/items/83451/export?format=json","diagnose":"/api/diagnose?url=https%3A//m.sohu.com/a/1076675399_115831%3Fscm%3D10001.325_13-325_13.0.0-0-0-0-0.5_1334"},"formats":{"full":{"id":83451,"title":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一 - Sohu","url":"https://m.sohu.com/a/1076675399_115831?scm=10001.325_13-325_13.0.0-0-0-0-0.5_1334","source":"Sohu","author":null,"published_at":"2026-09-16T02:29:00+00:00","locale":"zh","topic":"ai","tags":[],"excerpt":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一\n【CNMO科技消息】9月16日，在2026…","full_text":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一\n【CNMO科技消息】9月16日，在2026 vivo开发者大会上，vivo正式发布四款蓝心大模型，涵盖语音、端侧与云侧不同场景，进一步完善“以个人为中心的智能体大模型矩阵”。vivo表示，今年蓝心大模型将全面升级，核心目标是让系统拥有持续领先的“超强大脑”。\nvivo\n此次发布的四款模型分别是蓝心语音大模型、蓝心端侧大模型，以及蓝心云侧大模型Flash和Pro。其中，蓝心语音大模型采用全新端到端语音理解架构，融入更多个人化信息，在嘈杂环境下轻声说话、带口音、连续表达甚至中英混合，都能准确识别。\n蓝心端侧大模型（BlueLM-Nano 3B）主打实时感知与个人记忆沉淀。它能融合理解屏幕、图像、视频、文本和文件，不仅能看懂当下，还能记住用户的习惯偏好、用机状态、时空场景等。例如电话挂断后，系统可自动整理核心信息并生成记录。","reading_time_min":1,"extraction":{"state":"ok","confidence":0.9,"error":null,"explanation":"High confidence: full text extraction produced 394 characters.","diagnostics_url":"/api/diagnose?url=https%3A//m.sohu.com/a/1076675399_115831%3Fscm%3D10001.325_13-325_13.0.0-0-0-0-0.5_1334","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 394 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":394,"summary_length":52,"usable_text_length":394,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":394,"summary_length":52}}},"quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 394 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":394,"summary_length":52,"usable_text_length":394,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":394,"summary_length":52}},"actions":{"read":"/item/83451","export_markdown":"/api/items/83451/export?format=markdown","export_json":"/api/items/83451/export?format=json","diagnose":"/api/diagnose?url=https%3A//m.sohu.com/a/1076675399_115831%3Fscm%3D10001.325_13-325_13.0.0-0-0-0-0.5_1334"}},"digest":{"id":83451,"title":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一 - Sohu","url":"https://m.sohu.com/a/1076675399_115831?scm=10001.325_13-325_13.0.0-0-0-0-0.5_1334","source":"Sohu","topic":"ai","published_at":"2026-09-16T02:29:00+00:00","excerpt":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一 【CNMO科技消息】9月16日，在2026…","quality_bucket":"high","quality_reason":"High confidence: full text extraction produced 394 characters.","reading_time_min":1,"cluster_id":null},"card":{"display_title":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一 - Sohu","subtitle":"Sohu · 2026-09-16","summary":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一 【CNMO科技消息】9月16日，在2026…","badges":["quality:high"],"links":{"read":"/item/83451","original":"https://m.sohu.com/a/1076675399_115831?scm=10001.325_13-325_13.0.0-0-0-0-0.5_1334","diagnose":"/api/diagnose?url=https%3A//m.sohu.com/a/1076675399_115831%3Fscm%3D10001.325_13-325_13.0.0-0-0-0-0.5_1334"},"quality_warning":null},"export":{"title":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一 - Sohu","url":"https://m.sohu.com/a/1076675399_115831?scm=10001.325_13-325_13.0.0-0-0-0-0.5_1334","summary":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一\n【CNMO科技消息】9月16日，在2026…","source":"Sohu","date":"2026-09-16T02:29:00+00:00","content":"vivo连发四款AI大模型 蓝心Nano 3B六项评测第一\n【CNMO科技消息】9月16日，在2026 vivo开发者大会上，vivo正式发布四款蓝心大模型，涵盖语音、端侧与云侧不同场景，进一步完善“以个人为中心的智能体大模型矩阵”。vivo表示，今年蓝心大模型将全面升级，核心目标是让系统拥有持续领先的“超强大脑”。\nvivo\n此次发布的四款模型分别是蓝心语音大模型、蓝心端侧大模型，以及蓝心云侧大模型Flash和Pro。其中，蓝心语音大模型采用全新端到端语音理解架构，融入更多个人化信息，在嘈杂环境下轻声说话、带口音、连续表达甚至中英混合，都能准确识别。\n蓝心端侧大模型（BlueLM-Nano 3B）主打实时感知与个人记忆沉淀。它能融合理解屏幕、图像、视频、文本和文件，不仅能看懂当下，还能记住用户的习惯偏好、用机状态、时空场景等。例如电话挂断后，系统可自动整理核心信息并生成记录。","confidence":0.9,"diagnostics_url":"/api/diagnose?url=https%3A//m.sohu.com/a/1076675399_115831%3Fscm%3D10001.325_13-325_13.0.0-0-0-0-0.5_1334","quality_bucket":"high","failure_kind":"none","retryable":false,"quality_reason":"High confidence: full text extraction produced 394 characters.","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 394 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":394,"summary_length":52,"usable_text_length":394,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":394,"summary_length":52}},"tags":[],"format_contract_version":"news_item_formats.v1"}}}