JD.com has open-sourced its interactive audiovisual world model, JoyAI-EchoWM. This model is capable of generating synchronized video with sound, music, and speech, and responds in real-time to user navigation. It achieved a score of approximately 81.6 on the WBench Navigation benchmark. AI
IMPACT This release contributes to the growing field of multimodal AI, enabling more synchronized and interactive audiovisual content generation.
RANK_REASON Open-source release of a specific AI model.
Read on Mastodon — mastodon.social →
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →