3 articles tagged with #linear-attention. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers propose Kaczmarz Linear Attention (KLA), an improved algorithm for long-context language modeling that replaces empirically-learned coefficients with mathematically-derived key-norm-normalized step sizes. KLA outperforms existing linear attention baselines like Gated DeltaNet while maintaining computational efficiency and enabling stable processing of up to 65K token contexts.
MiniCPM-SALA introduces a 9B-parameter hybrid language model architecture that combines sparse and linear attention mechanisms to handle ultra-long contexts up to 1M tokens. The model achieves 3.5x faster inference than full-attention models while reducing training costs by 75% through a continual training framework that transforms existing Transformer models.
Researchers reveal that Test-Time Training (TTT) with KV binding, previously understood as online meta-learning for memorization, can actually be reformulated as a learned linear attention operator. This new perspective explains previously puzzling behaviors and enables architectural simplifications and efficiency improvements.
