No article text was recorded for this version.
hardware-unfriendly sparsity
Version 1 of 1238 papers265 conceptsfrozen 2026-10-04
Papers in this version
- Blog: FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel
- Blog: A-VL: Adaptive Attention for Large Vision-Language Models
- Blog: Only 5\% Attention Is All You Need: Efficient Long-range Document-level Neural Machine Translation
- Blog: Only 5% Attention Is All You Need: Efficient Long-range Document-level Neural Machine Translation
- Blog: X-former Elucidator: Reviving Efficient Attention for Long Context Language Modeling
- Blog: SeerAttention-R: Sparse Attention Adaptation for Long Reasoning
- Blog: AdaSplash-2: Faster Differentiable Sparse Attention
- Blog: VideoNSA: Native Sparse Attention Scales Video Understanding
- Blog: InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation
- Blog: Big Bird: Transformers for Longer Sequences
- Blog: Fast Causal Attention with Dynamic Sparsity
- Blog: Learning Adaptive Axis Attentions in Fine-tuning: Beyond Fixed Sparse Attention Patterns
- Blog: Multimodal Phased Transformer for Sentiment Analysis
- Blog: CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
- Blog: Efficient Content-Based Sparse Attention with Routing Transformers
- Blog: What Dense Graph Do You Need for Self-Attention?
- Blog: AdaSplash: Adaptive Sparse Flash Attention
- Blog: DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidance
- Blog: CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
- Blog: SEA: Sparse Linear Attention with Estimated Attention Mask
- Blog: Faster Neighborhood Attention: Reducing the O(n^2) Cost of Self Attention at the Threadblock Level
- Blog: Quadtree Attention for Vision Transformers
- Blog: FG-Attn: Leveraging Fine-Grained Sparsity In Diffusion Transformers
- Blog: A-VL: Adaptive Attention for Large Vision-Language Models
- Blog: Does Long-Term Series Forecasting Need Complex Attention and Extra Long Inputs?
- Blog: SSSD: Simply-Scalable Speculative Decoding
- Blog: Tractable Transformers for Flexible Conditional Generation
- Blog: SeerAttention: Self-distilled Attention Gating for Efficient Long-context Prefilling
- Blog: SSH-Net: A Self-Supervised and Hybrid Network for Noisy Image Watermark Removal
- Blog: Memory-efficient Transformers via Top-k Attention
- Blog: Body Transformer: Leveraging Robot Embodiment for Policy Learning
- Blog: Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention
- Blog: Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers
- Blog: Fast Video Generation with Sliding Tile Attention
- Blog: CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention
- Blog: TransNeXt: Robust Foveal Visual Perception for Vision Transformers
- Blog: Graph Conditioned Sparse-Attention for Improved Source Code Understanding
- Blog: NOSA: Native and Offloadable Sparse Attention
- Blog: Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
- Blog: Rectified Sparse Attention
- Blog: HilbertA: Hilbert-Curve–Aligned Sparse Attention for 2D Structured Data
- Blog: A Simple and Effective L2 Norm-Based Strategy for KV Cache Compression
- Blog: FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
- Blog: ProxyAttn: Guided Sparse Attention via Representative Heads
- Blog: TileSparse: Arithmetic-Intensity-Aware Sparse Attention for Compute-Bound LLM Decoding
- Blog: SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator
- Blog: Taipan: Efficient and Expressive State Space Language Models with Selective Attention
- Blog: BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation
- Blog: DEFA: Efficient Deformable Attention Acceleration via Pruning-Assisted Grid-Sampling and Multi-Scale Parallel Processing
- Blog: BSA: Ball Sparse Attention for Large-scale Geometries
- Blog: Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design
- Blog: Long-Context Modeling with Dynamic Hierarchical Sparse Attention for On-Device LLMs
- Blog: MoDeGPT: Modular Decomposition for Large Language Model Compression
- Blog: Scaling Local Self-Attention for Parameter Efficient Visual Backbones
- Blog: BiFormer: Vision Transformer with Bi-Level Routing Attention
- Blog: Faster Neighborhood Attention: Reducing the O(n^2) Cost of Self Attention at the Threadblock Level
- Blog: SparQ Attention: Bandwidth-Efficient LLM Inference
- Blog: BiSparse-AAS: Bilinear Sparse Attention and Adaptive Spans Framework for Scalable and Efficient Text Summarization
- Blog: db-SP: Accelerating Sparse Attention for Visual Generative Models with Dual-Balanced Sequence Parallelism
- Blog: Blockwise Self-Attention for Long Document Understanding
Showing 60 of 238 papers.
History & citation
Current · Permanent link
- Hardware-Aware Sparse Attention for Long Contexts merged into this direction (59% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_hardware_unfriendly_sparsity_82b069ca,
title = {hardware-unfriendly sparsity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/hardware-unfriendly-sparsity/rdr_82b069ca8d5a404b8fe3ec888c3312ba},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_hardware_unfriendly_sparsity_82b069ca_v1,
title = {hardware-unfriendly sparsity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/hardware-unfriendly-sparsity/rdr_82b069ca8d5a404b8fe3ec888c3312ba/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}