Search papers, labs, and topics across Lattice.
Shanghai Jiao Tong University
2
0
4
TF-MoE achieves a remarkable +3.8 dB improvement in speech separation performance while keeping computational costs low, making it ideal for edge-device applications.
Achieve up to 52.5% compression in LLM chain-of-thought reasoning *while improving* accuracy by dynamically calibrating CoT length.
