paper-with-me

Papers

$π$-Attention: Online Efficient Sparse Transformers for Long-Context Modeling

2025-11-12 · Dong Liu, Yanxuan Yu arxiv

Sparse attention is crucial in long-context Transformers, which restricts each token to a limited neighborhood and thereby reduces the quadratic cost of full self-attention. Local windows capture nearby context effectively, yet they induce a receptive-field bottleneck for dependencies beyond the window, limiting long-range modeling under moderate depth. In this paper, we propose $π$-Attention, an \emph{online efficient} sparse attention operator: as tokens arrive, each step maintains a streaming working set of local neighbors plus a $π$-indexed long-range fetch, fused by an adaptive prior under a shared softmax. Rather than materializing a global sparse mask in advance, $π$-Attention computes attention on the live working set with hierarchy-aware IO. We analyze causal reachability and minimum depth under this online rule, and show per-step cost remains $\mathcal{O}(k)$. Experiments on language modeling, Long Range Arena, and efficiency profiling---across 4K--32K context lengths---show consistent gains over local-window and other sparse baselines, approaching dense attention quality at linear cost.

📄 PDF Abstract BibTeX arXiv:2511.10696

Code (0)

등록된 구현이 없습니다.

Tasks

Long-range modeling

Similar Papers 제목 키워드 기반

InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models

2025-12-09 · Hongyuan Tao, Bencheng Liao, Shaoyu Chen, Haoran Yin 외 arxiv

Vision-Language Models (VLMs) are increasingly tasked with ultra-long multimodal understanding. While linear architectures offer constant computation and memory footprints, they often struggle with high-frequency visual …

VMonarch: Efficient Video Diffusion Transformers with Structured Attention

2026-01-29 · Cheng Liang, Haoxian Chen, Liang Hou, Qi Fan 외 arxiv

The quadratic complexity of the attention mechanism severely limits the context scalability of Video Diffusion Transformers (DiTs). We find that the highly sparse spatio-temporal attention patterns exhibited in Video DiT…

SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers

2026-07-03 · Jianing Deng, Yuanzhe Li, Jialu Wang, Song Wang 외 arxiv

Feed-forward 3D reconstruction (F3R) transformers have recently achieved remarkable success. However, scaling them to long image sequences remains challenging, as the quadratic complexity of cross-view global attention q…

Camera Pose Estimation3D Reconstruction

Lifelong In-Context Learning with Transformers Requires Parametric Forms of Attention

2026-06-24 · Luke McDermott, Robert W. Heath, Rahul Parhi arxiv

Lifelong continual learning remains an obstacle on the path to human-like intelligence. Modern transformers show sparks of intelligence with in-context learning. The quadratic nature of attention, however, prohibits tran…

Continual Learning

Scaling Attention via Feature Sparsity

2026-03-17 · Yan Xie, Tiansheng Wen, Tangda Huang, Bo Chen 외 arxiv

Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce this cost along the sequence axis through local windows, kernel approximations, or token-level…