4 papers · 1 filter
Done Is Better than Perfect: Unlocking Efficient Reasoning by Structured Multi-Turn Decomposition
Zihao Zeng, Xuyao Huang, Boxiu Li +2
Large Reasoning Models (LRMs) are criticized for the excessively lengthy Chain-of-Thought (CoT) to derive the final answer, suffering from high first-token and overall latency. Typ…
RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability
Yichi Zhang, Zihao Zeng, Dongbai Li +3
Large Reasoning Models (LRMs), such as OpenAI o1 and DeepSeek-R1, have been rapidly progressing and achieving breakthrough performance on complex reasoning tasks such as mathematic…
ExpertFlow: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling
Xin He, Shunkang Zhang, Kaijie Tang +8
Sparse Mixture-of-Experts (MoE) models can outperform dense large language models at similar computation by activating only a small set of experts per token. However, stacking many…
AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models
Zihao Zeng, Yibo Miao, Hongcheng Gao +2
Mixture of experts (MoE) has become the standard for constructing production-level large language models (LLMs) due to its promise to boost model capacity without causing significa…