Dialogue Systems

StreamingDialogue revolutionizes prolonged dialogue learning by compressing long contexts into conversational attention sinks, minimizing information loss and achieving a 4x speedup with 18x less memo…

AI agents developed a communication system using spatial relationships, achieving over 90% accuracy in conveying relative positions of objects within a scene.

New APC metric precisely quantifies & optimizes global faithfulness in persona-driven role-playing, offering a fine-grained, explainable evaluation and improving AI character consistency.

Unified Spoken Dialog Model (USDM) directly generates coherent spoken responses with natural prosody, surpassing cascaded baselines and enhancing natural conversation in speech-enabled LLMs.

Multi-turn RLHF surpasses single-turn methods by aligning LLMs with human preferences across entire conversations, not just individual turns. A novel mirror-descent algorithm, MTPO, is introduced, pr…

CoVoMix: Generating human-like, multi-speaker conversations with zero-shot speech synthesis.

AI agents learn human-like communication, combining semantic categorization and pragmatic context-sensitive reasoning, through a novel information-theoretic framework.

iAgents: a novel multi-agent system leveraging LLMs, overcomes information asymmetry by mirroring human social networks to enable effective collaboration in complex tasks, achieving high accuracy in d…

This paper introduces a novel full-duplex speech dialogue system based on LLMs, achieving significantly reduced response latency and higher interruption precision compared to half-duplex systems.