Dongjie Fu

Vox-Infinity: Benchmarking the Limits of Long-Context Spoken Language Models

MARS-Sep: Multimodal-Aligned Reinforced Sound Separation

OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios

Character Beyond Speech: Leveraging Role-Playing Evaluation in Large Audio Language Models via Reinforcement Learning

VoxDialogue: Can Spoken Dialogue Systems Understand Information Beyond Words?

OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios

Noise-Robust Audio-Visual Speech-Driven Body Language Synthesis