MiniCPM5-2B-DSpark

Papers using or citing this model 2

• MiniCPM4: Ultra-Efficient LLMs on End Devices 60 citations · 2025 · arXiv (Cornell University) · arXiv

  This paper introduces MiniCPM4, a highly efficient large language model (LLM) designed explicitly for end-side devices. We achieve this efficiency through systematic innovation in four key dimensions: model architecture, training data,...

• DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation 50 citations · 2026 · arXiv (Cornell University) · arXiv

  Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification. While recent parallel drafters efficiently propose long token sequences in a single forward pass, they suffer...