1 citations · 1 across the 17 of their papers we have counts for
5 papers · 1 filter
Maximum Score Routing For Mixture-of-Experts
Bowen Dong, Yilong Fan, Yutao Sun +4
Routing networks in sparsely activated mixture-of-experts (MoE) dynamically allocate input tokens to top-k experts through differentiable sparse transformations, enabling scalable…
Novel Parasitic Dual-Scale Modeling for Efficient and Accurate Multilingual Speech Translation
Chenyang Le, Yinfeng Xia, Huiyan Li +4
Recent advancements in speech-to-text translation have led to the development of multilingual models capable of handling multiple language pairs simultaneously. However, these unif…
Efficient Attention Mechanisms for Large Language Models: A Survey
Yutao Sun, Zhenyu Li, Yike Zhang +4
Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamen…
MFLA: Monotonic Finite Look-ahead Attention for Streaming Speech Recognition
Yinfeng Xia, Huiyan Li, Chenyang Le +4
Applying large pre-trained speech models like Whisper has shown promise in reducing training costs for various speech tasks. However, integrating these models into streaming system…
The Self-Improvement Paradox: Can Language Models Bootstrap Reasoning Capabilities without External Scaffolding?
Yutao Sun, Mingshuai Chen, Tiancheng Zhao +3
Self-improving large language models (LLMs) -- i.e., to improve the performance of an LLM by fine-tuning it with synthetic data generated by itself -- is a promising way to advance…