稀疏加速论文趋势 2023–2026

主要结论

• 稀疏加速论文从 2023 年的 54 篇增长到 2026 年的 89 篇，三年间扩大到约 1.6 倍。
• NeurIPS 是发稀疏加速论文最多的会议，2023–2026 年共 80 篇，占四个会议总量的 31%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 13 篇。
• 在「硬件与编译」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的端侧推理是 4.0 倍，稀疏加速是 1.6 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026AC/DC on a Budget -- Alternating Sparse Phases
• ICML 2026An Evidential Route to Asymptotic Bayes Optimality under Sparsity
• ICLR 2026Hilbert-Guided Sparse Local Attention
• CVPR 2026Improving Sparse Autoencoder with Dynamic Attention
• NeurIPS 2025Bilevel Network Learning via Hierarchically Structured Sparsity
• ICML 2025COGNATE: Acceleration of Sparse Tensor Programs on Emerging Hardware using Transfer Learning
• ICLR 2025Beyond Worst-Case Dimensionality Reduction for Sparse Vectors
• CVPR 2025ICP: Immediate Compensation Pruning for Mid-to-high Sparsity
• NeurIPS 2024ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration
• ICML 2024Accelerating Transformer Pre-training with 2:4 Sparsity
• ICLR 2024Adaptive Sharpness-Aware Pruning for Robust Sparse Networks
• CVPR 2024Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement
• NeurIPS 2023Dynamic Sparsity Is Channel-Level Sparsity Learner
• ICML 2023Conformalization of Sparse Generalized Linear Models
• ICLR 2023Bit-Pruning: A Sparse Multiplication-Less Dot-Product
• CVPR 2023Adaptive Channel Sparsity for Federated Learning Under System Heterogeneity
• NeurIPS 2026Beyond Masked Sparsity: SNACK Enables Truly Sparse Neural Networks on GPU
• ICML 2026FlashSketch: Sketch-Kernel Co-Design for Fast Sparse Sketching on GPUs
• ICLR 2026Identifiability Challenges in Sparse Linear Ordinary Differential Equations
• CVPR 2026Revisiting Pose Sensitivity in Splat-based Computed Tomography under Sparse-view Reconstruction

全部稀疏加速论文

共 260 篇，第 2 / 6 页

51. ICML 2026Narrowing the ANN–SNN Gap for Continuous 1D Temporal Signal Classification with Multi-Scale Temporal Encoding and Sparsity-Regularized Transform Encoding
52. ICML 2026Prism: Spectral-Aware Block-Sparse Attention
53. ICML 2026RSTR: Reducing SpatioTemporal Redundancy in Diffusion Transformers
54. ICML 2026RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models
55. ICML 2026Size Transferability of Graph Convolutional Networks across Sparsity: A Generalized Graphon Perspective
56. ICML 2026SlideSparse: Fast and Flexible (2N-2):2N Structured Sparsity
57. ICML 2026SparseOpt: Addressing Normalization-induced Gradient Skew in Sparse Training
58. ICML 2026Sparser Block-Sparse Attention via Token Permutation
59. ICML 2026Weight-sparse transformers have interpretable circuits
60. ICML 2026When Does Sparsity Mitigate the Curse of Depth in LLMs
61. NeurIPS 2026AC/DC on a Budget -- Alternating Sparse Phases
62. NeurIPS 2026Asymmetric Scaling Laws from Sparse Features
63. NeurIPS 2026Attribute-Efficient Learning of Sparse Halfspaces with Constant Malicious Noise Rate
64. NeurIPS 2026Beyond Masked Sparsity: SNACK Enables Truly Sparse Neural Networks on GPU
65. NeurIPS 2026Cannistraci-Hebb Channel-wise Dynamic Sparse Training of Convolutional Neural Networks with Contextual Modulation
66. NeurIPS 2026Coarse-to-Fine 3D MRI Reconstruction via Resolution-Agnostic Neural Operators
67. NeurIPS 2026Colour me shocked: Exact Molecular Hessians from MLIPs in O(N) time using sparse differentiation!
68. NeurIPS 2026Contribution-Aware Structured Sparsity for Model Merging
69. NeurIPS 2026Direct Acceleration of Stochastic Root-Finding Without Variance Reduction and Regularization
70. NeurIPS 2026Distribution Free Fourier Sparsity Testing
71. NeurIPS 2026Effectiveness of Curriculum Learning Depends on Reward Sparsity and Competing Optima
72. NeurIPS 2026Efficient Fine-Tuning for Structured Sparsity Under Group Repartitioning
73. NeurIPS 2026Flow Matching from Viewpoint of Proximal Operators
74. NeurIPS 2026Inference-time Alignment via Sparse Junction Steering
75. NeurIPS 2026Intrinsically Interpretable Attention via Sparse Post-Training
76. NeurIPS 2026Inverting Retargeting: Humanoid Datasets Remember Their Operators
77. NeurIPS 2026Learning Event-to-Field Operators Without Interpolation
78. NeurIPS 2026Long-Context Language Models Require Extreme Sparsity in Context Dimension
79. NeurIPS 2026On the Sparsity of Direct Preference Optimization: Weight Disentanglement in the NTK Regime
80. NeurIPS 2026On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning
81. NeurIPS 2026OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
82. NeurIPS 2026Perfect Parallelization in Mini-Batch SGD with Classical Momentum Acceleration
83. NeurIPS 2026Posterior Contraction Rates for sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces
84. NeurIPS 2026Sparse blind deconvolution via thresholded Wirtinger flow
85. NeurIPS 2026Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
86. NeurIPS 2026Sparse Sum-of-Squares Layers for Certified Learning
87. NeurIPS 2026SVDP: Training-Free Contextual Sparsity Predictors for Fast LLM Inference
88. NeurIPS 2026The Sparsity Whisperer
89. NeurIPS 2026Transferable SCF-Acceleration through Solver-Aligned Initialization Learning
90. CVPR 2025CASP: Compression of Large Multimodal Models Based on Attention Sparsity
91. CVPR 2025ICP: Immediate Compensation Pruning for Mid-to-high Sparsity
92. CVPR 2025MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds
93. CVPR 2025S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splatting
94. CVPR 2025SINR: Sparsity Driven Compressed Implicit Neural Representations
95. ICLR 2025Beyond Worst-Case Dimensionality Reduction for Sparse Vectors
96. ICLR 2025Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries
97. ICLR 2025DPaI: Differentiable Pruning at Initialization with Node-Path Balance Principle
98. ICLR 2025Dynamic Low-Rank Sparse Adaptation for Large Language Models
99. ICLR 2025Efficient Sparse PCA via Block-Diagonalization
100. ICLR 2025From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency

常见问题

2023–2026 年四大会议一共有多少篇稀疏加速论文？

共 260 篇，按年份分别是 2023 年 54 篇、2024 年 53 篇、2025 年 64 篇、2026 年 89 篇。

NeurIPS 2026 有多少篇稀疏加速论文？

NeurIPS 2026 有 29 篇稀疏加速论文，上一届是 21 篇。

ICLR 2026 有多少篇稀疏加速论文？

ICLR 2026 有 24 篇稀疏加速论文，上一届是 16 篇。

ICML 2026 有多少篇稀疏加速论文？

ICML 2026 有 24 篇稀疏加速论文，上一届是 22 篇。

CVPR 2026 有多少篇稀疏加速论文？

CVPR 2026 有 12 篇稀疏加速论文，上一届是 5 篇。

哪个会议的稀疏加速论文最多？

NeurIPS，2023–2026 年共 80 篇。