Publications

Fei Tian (2025). Chronological Thinking in Full-Duplex Spoken Dialogue Language Models.
PDF
Fei Tian (2025). [Coming soon!] Step-Audio R1: Achieving Gemini 2.5 Pro-Level Reasoning in a Zero-Latency Speech LLM.
Fei Tian (2025). [Coming soon!] Step MPS: Mind-Paced Speaking Framework.
Fei Tian (2025). [Coming soon!] Step EditX: Next-Generation Conversational Speech Editing Model.
Fei Tian (2025). Step-Audio 2 Technical Report.
PDF
Fei Tian (2025). Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model.
PDF
Fei Tian (2025). Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction.
PDF