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 Machine Learning
Sep 24
Attention Routing Stabilizes Early: Working-Set Inference for Recurrent Language Models
The paper investigates how attention dynamics evolve across recurrent depth in language models, finding that attention support stabilizes early while hidden states and outputs take longer. It proposes WISE, a training‑free method that uses full attention in early steps and then reuses the discovered sparse working set for later steps, preserving performance on multi‑hop QA tasks. Experiments show that WISE maintains quality up to 2K context, offers measurable speedups, and highlights the importance of recurrent discovery of attention support.
arXiv Computation and Language
Oct 8
Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position
arXiv:2610.10114v1 Announce Type: new Abstract: The architectural design of Large Language Models (LLMs) is shifting from traditional full-attention-only models to hybrid models, which combine differ...
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
Sep 3
Language Models Can Control Their Own Attention
The paper introduces Declarative Attention (DA), a protocol that lets language models explicitly declare which parts of their context to focus on during generation. By partitioning decoding into full-context, region-specific, and recent-output-only modes, the inference engine can skip large portions of the KV cache, dramatically reducing attended tokens. Experiments on 15 long-context tasks with off-the-shelf models show significant savings (52.0% and 31.1% reductions) with only modest accuracy drops that diminish as model size increases.
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.