3 papers
cs.AI2026
SAEM: Stage-Aware Expert Management for Memory-Efficient MoE Inference in Chain-of-Thought Reasoning
Yujie Zhang, Bin Gao, Tulika Mitra
Chain-of-thought (CoT) prompting improves LLM reasoning by decomposing complex problems into intermediate steps, but its sequential nature increases decoding latency and memory usa…
cs.AR2026
Accelerating Multi-Scale Deformable Attention Using Near-Memory-Processing Architecture
Huize Li, Qinggang Wang, Bing Gao +3
Multi Scale Deformable Attention (MSDAttn) has become a fundamental component in various vision tasks due to its effective multi scale grid sampling (MSGS). However, its reliance o…
cs.CL2025
AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference
Zhuomin He, Yizhen Yao, Pengfei Zuo +4
Long-context large language models (LLMs) inference is increasingly critical, motivating a number of studies devoted to alleviating the substantial storage and computational costs…