arXiv Machine Learning
Sliding-window beats linear attention
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 23
LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning
arXiv:2607. 19358v1 Announce Type: new Abstract: Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context lengths under the test-time scaling paradigm.
arXiv AI
Jun 11
Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning
arXiv:2606. 11634v1 Announce Type: new Abstract: The rapid progress of reasoning and agentic large language models (LLMs) has increased the demand for long-context inference, but self-attention (SA) scales quadratically with context length.
arXiv AI
Jun 10
Blurry Window Attention
arXiv:2606. 09862v1 Announce Type: cross Abstract: The Softmax Attention operation in Transformer language models has a quadratic complexity in the sequence length and a growing state size in the form of KV cache, which becomes a bottleneck in long context scenarios.
arXiv AI
Jul 7
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
arXiv:2607. 02980v1 Announce Type: cross Abstract: Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense attention.
arXiv AI
Jun 9
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
arXiv:2605. 16928v2 Announce Type: replace-cross Abstract: Long-context inference in large language models is bottlenecked by the quadratic cost of full attention.
arXiv Machine Learning
Jun 16
LoLA: Low-Rank Linear Attention With Sparse Caching
arXiv:2505. 23666v3 Announce Type: replace-cross Abstract: The per-token cost of transformer inference scales with context length, preventing its application to lifelong in-context learning.