3 citations · 4 across the 4 of their papers we have counts for
3 papers · 1 filter
Kronecker Product Attention: Memory-Efficient KV Compression via Structured Factorization
Bahareh Nikpour, Hossein Rajabzadeh, Maryam Dialameh +2
Efficient autoregressive generation is increasingly limited by the memory footprint of the key-value (KV) cache, which grows linearly with sequence length, batch size, and model de…
Large Language Models with At Most One Spike per Neuron
Zhuoya Zhao, Parsa Omidi, Aref Jafari +1
Leveraging their inherent sparse event-driven computation, spiking neural networks (SNNs) offer a promising path toward energy-efficient large language models (LLMs). Time-to-first…
Hierarchical Chain-of-Thought: Enhancing LLM Reasoning Performance and Efficiency
Xingshuai Huang, Derek Li, Bahareh Nikpour +1
Chain-of-Thought (CoT) prompting has significantly improved the reasoning capabilities of large language models (LLMs). However, conventional CoT often relies on unstructured, flat…