SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

T1Covered by 1 source · first reported by arXiv at 24 Sept, 04:00 UTC

arXiv:2609.26780v2 Announce Type: cross Abstract: Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distinguish who said what, whom each statement concerns, how individuals perceive one another, what…

science

Sources

• T1SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party DialoguearXiv24 Sept, 04:00