Lu Lu

ParaS2S: Benchmarking and Aligning Spoken Language Models for Paralinguistic-aware Speech-to-Speech Interaction

End-to-end Listen, Look, Speak and Act

DuPO: Enabling Reliable Self-Verification via Dual Preference Optimization

Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents

Partner-Bench: Evaluating Visually-Grounded IQ and Interactive EQ in Audio-Visual Dialogue

SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation

SALMONN-omni: A Speech Understanding and Generation LLM in a Codec-free Full-duplex Framework