English(EN) JD.com Open-Sources JoyAI-EchoWM Interactive Audiovisual World Model at JDD

京东开源视听模型JoyAI-EchoWM

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 09:01

京东已开源其交互式视听世界模型JoyAI-EchoWM以及EchoWM-Flash。该模型在WBench导航基准测试中取得了约81.6-81.7的分数，展示了统一的相机意图控制和原生的音视频生成能力。京东还宣布计划开发一个大型国内GPU集群及其Superbrain 3.0物流系统。 AI

影响此次发布为开源社区的多模态AI能力做出了贡献，可能为音视频生成和导航领域带来新的应用。

排序理由多模态模型开源发布，并附有基准测试分数。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 35 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 多模态模型开源发布，并附有基准测试分数。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: model release, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

Pandaily TIER_1 English(EN) · [email protected] (Pandaily) · 2026-09-10 09:01

京东在JDD上开源JoyAI-EchoWM交互式视听世界模型

JD.com open-sourced JoyAI-EchoWM and EchoWM-Flash at JDD, scoring about 81.6–81.7 on WBench Navigation with unified camera-intent control and native audio-video generation, alongside plans for a large domestic GPU cluster and logistics Superbrain 3.0.