MiniCPM-SALA

Papers using or citing this model 2

• InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation 32 citations · 2025 · arXiv (Cornell University) · arXiv

  Long-sequence processing is a critical capability for modern large language models. However, the self-attention mechanism in the standard Transformer architecture faces severe computational and memory bottlenecks when processing long...

• Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts 17 citations · 2026 · arXiv (Cornell University) · arXiv

  Hybrid Transformer architectures, which combine softmax attention blocks and recurrent neural networks (RNNs), have shown a desirable performance-throughput tradeoff for long-context modeling, but their adoption and studies are hindered...