4 papers
SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE Models
Juntong Wu, Jialiang Cheng, Fuyu Lv +2
Mixture-of-Experts (MoE) architectures employ sparse activation to deliver faster training and inference with higher accuracy than dense LLMs. However, in production serving, MoE m…
SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning
Peidong Wang, Zhiming Ma, Xin Dai +8
Existing fraud detection methods predominantly rely on transcribed text, suffering from ASR errors and missing crucial acoustic cues like vocal tone and environmental context. This…
MoH: Multi-Head Attention as Mixture-of-Head Attention
Peng Jin, Bo Zhu, Li Yuan +1
In this work, we upgrade the multi-head attention mechanism, the core of the Transformer model, to improve efficiency while maintaining or surpassing the previous accuracy level. W…
MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts
Peng Jin, Bo Zhu, Li Yuan +1
In this work, we aim to simultaneously enhance the effectiveness and efficiency of Mixture-of-Experts (MoE) methods. To achieve this, we propose MoE++, a general and heterogeneous…