Scaling Context Requires Rethinking Attention

• URL: http://arxiv.org/abs/2507.04239v1
• Date: Sun, 06 Jul 2025 04:15:34 GMT
• Title: Scaling Context Requires Rethinking Attention
• Authors: Carles Gelada, Jacob Buckman, Sean Zhang, Txus Bach,
• Abstract summary: We argue that neither transformers nor sub-quadratic architectures are well suited to training at long sequence lengths.<n>We introduce power attention, an architectural layer for linear-cost sequence modeling whose state size can be adjusted independently of parameters.<n>Our experiments on the in-context learning of power attention shows that these models dominate both exponential attention and linear attention at long-context training.
• Score: 5.923968936360167
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We argue that neither transformers nor sub-quadratic architectures are well suited to training at long sequence lengths: the cost of processing the context is too expensive in the former, too inexpensive in the latter. Approaches such as sliding window attention which reduce the cost-per-token of a transformer impair in-context learning, and so are also unsuitable. To address these limitations, we introduce power attention, an architectural layer for linear-cost sequence modeling whose state size can be adjusted independently of parameters, unlocking the advantages of linear attention on practical domains. We develop and open-source a set of GPU kernels for efficient power attention, identifying a novel pattern of operation fusion to avoid memory and bandwidth bottlenecks. Our experiments on the in-context learning of power attention shows that these models dominate both exponential attention and linear attention at long-context training.

Related papers

• Log-Linear Attention [81.09631871212211]
  This paper develops log-linear attention, an attention mechanism that balances linear attention's efficiency and the expressiveness of softmax attention.<n>We show that with a particular growth function, log-linear attention admits a similarly matmul-rich parallel form whose compute cost is log-linear in sequence length.<n>Log-linear attention is a general framework and can be applied on top of existing linear attention variants.
  arXiv  Detail & Related papers  (2025-06-05T08:44:51Z)
• CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up [64.38715211969516]
  We introduce a convolution-like local attention strategy termed CLEAR, which limits feature interactions to a local window around each query token.<n>Experiments indicate that, by fine-tuning the attention layer on merely 10K self-generated samples for 10K iterations, we can effectively transfer knowledge from a pre-trained DiT to a student model with linear complexity.
  arXiv  Detail & Related papers  (2024-12-20T17:57:09Z)
• Bridging the Divide: Reconsidering Softmax and Linear Attention [116.34723260730405]
  We present two key perspectives to understand and alleviate the limitations of linear attention.<n>We prove that linear attention is not injective, which is prone to assign identical attention weights to different query vectors.<n> Secondly, we confirm that effective local modeling is essential for the success of Softmax attention, in which linear attention falls short.
  arXiv  Detail & Related papers  (2024-12-09T15:44:22Z)
• Continual Low-Rank Scaled Dot-product Attention [67.11704350478475]
  We introduce a new formulation of the Scaled-product Attention based on the Nystr"om approximation that is suitable for Continual Inference.<n>In experiments on Online Audio Classification and Online Action Detection tasks, the proposed Continual Scaled Dot-product Attention can lower the number of operations by up to three orders of magnitude.
  arXiv  Detail & Related papers  (2024-12-04T11:05:01Z)
• MAS-Attention: Memory-Aware Stream Processing for Attention Acceleration on Resource-Constrained Edge Devices [24.1144641404561]
  We propose a scheme for exact attention inference acceleration on memory-constrained edge accelerators.<n>We show up to 2.75x speedup and 54% reduction in energy consumption as compared to the state-of-the-art attention fusion method (FLAT) in the edge computing scenario.
  arXiv  Detail & Related papers  (2024-11-20T19:44:26Z)
• Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences [60.489682735061415]
  We propose CHELA, which replaces state space models with short-long convolutions and implements linear attention in a divide-and-conquer manner. Our experiments on the Long Range Arena benchmark and language modeling tasks demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2024-06-12T12:12:38Z)
• Lean Attention: Hardware-Aware Scalable Attention Mechanism for the Decode-Phase of Transformers [4.674454841332859]
  Transformer-based models have emerged as one of the most widely used architectures for natural language processing.<n>These huge models are memory hungry and incur significant inference latency even on cutting edge AI-accelerators.<n>We propose LeanAttention, a scalable technique of computing self-attention for the token-generation phase.
  arXiv  Detail & Related papers  (2024-05-17T00:52:39Z)
• In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness [43.70647711168682]
  We show the role of softmax attention in an ICL setting where each context encodes a regression task. We show that an attention unit learns a window that it uses to implement a nearest-neighbors predictor adapted to the landscape of the pretraining tasks. We also show that on low-rank, linear problems, the attention unit learns to project onto the appropriate subspace before inference.
  arXiv  Detail & Related papers  (2024-02-18T16:37:32Z)
• FLatten Transformer: Vision Transformer using Focused Linear Attention [80.61335173752146]
  Linear attention offers a much more efficient alternative with its linear complexity. Current linear attention approaches either suffer from significant performance degradation or introduce additional computation overhead. We propose a novel Focused Linear Attention module to achieve both high efficiency and expressiveness.
  arXiv  Detail & Related papers  (2023-08-01T10:37:12Z)
• The Devil in Linear Transformer [42.232886799710215]
  Linear transformers aim to reduce the quadratic space-time complexity of vanilla transformers. They usually suffer from degraded performances on various tasks and corpus. In this paper, we identify two key issues that lead to such performance gaps.
  arXiv  Detail & Related papers  (2022-10-19T07:15:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.