PERSIST: Who-What-When Memory Across Sessions for Full-Duplex Spoken Dialogue
cs.AI
Submitted: 2026-10-06
Updated: 2026-10-06
Sources
- TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions
- Common Voice: A Massively-Multilingual Speech Corpus
- GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
- Moshi: a speech-text foundation model for real-time dialogue
- CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
- Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues
- Efficient Temporal-aware Matryoshka Adaptation for Temporal Information Retrieval
- TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
- VIBEVOICE-ASR Technical Report
- MSU-Bench: Towards Speaker-Centric Understanding in Conversational Multi-Speaker Scenarios
- VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction
- A-MEM: Agentic Memory for LLM Agents
- GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations
- SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems