Jun Zhang

4 papers Guizhou University

• CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
• Fourier Analysis Network
• SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation
• SMARTraj$^2$: A Stable Multi-City Adaptive Method for Multi-View Spatio-Temporal Trajectory Representation Learning