MS-GLA: Multi-Scale Gated Linear Attention for Addressing Representational Bottlenecks via Multi-Temporal Resolution

arXiv:2609.35664 · cs.CL, cs.AI · Submitted 2026-09-28 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/fla-org/flash-linear-attention

Terminology

• Perplexity — 19× in this paper · explained in 3 episodes
• Transformer — 16× in this paper · explained in 2 episodes
• Gated Linear Attention — 14× in this paper
• Generalization — 7× in this paper · explained in 13 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• Robustness — 6× in this paper · explained in 5 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• State Space Model — 3× in this paper
• Ablation — 2× in this paper · explained in 1 episode
• Attention Mechanism — 2× in this paper · explained in 3 episodes
• Core — 2× in this paper · explained in 2 episodes
• F1 Score — 2× in this paper · explained in 3 episodes
• Wavelet Transform — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Hybrid Architectures — 1× in this paper · explained in 3 episodes
• Multi-Resolution Analysis — 1× in this paper
• Parameter Efficiency — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes

Sources

• Spectral State Space Models
• Simple linear attention language models balance the recall-throughput tradeoff
• MoM: Linear Sequence Modeling with Mixture-of-Memories
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Training Compute-Optimal Large Language Models
• Decoupled Weight Decay Regularization
• Hierarchical Transformers Are More Efficient Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering