Launched multimodal memory capabilities
The story so far
openJiuwen has launched its multimodal memory capability OmniMem-Lens, which understands video events through visual and auditory dual streams, with recall accuracy improved by up to 45.7% and online Q&A latency reduced by up to 97%. This technology segments memory based on real events, establishing a three-layer memory structure to achieve offline construction and online retrieval. OmniMem-Lens has officially launched in the openJiuwen Agent-Memory 0.2.0 version, welcome to experience and co-build.
AI-written from the reports · Updated 15 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- QbitAIHow does openJiuwen Agent-Memory achieve audio-visual dual-stream memory, understand long videos?
openJiuwen Agent-Memory 0.2.0 version launched multimodal memory capabilities OmniMem-Lens, which understands video events through visual and auditory dual streams, recall accuracy improved by up to 45.7%, and online Q&A latency reduced by up to 97%. This technology segments memory according to real events, establishing a three-layer memory structure to achieve offline construction and online query, demonstrating outstanding performance on the EgoLife-QA benchmark set, with longer videos showing more significant latency reduction.