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 89 篇，第 1 / 2 页

1. CVPR 2026Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensors
2. CVPR 2026FSFSplatter Geometrically Accurate Reconstruction with Free Sparse-view Images within 2
3. CVPR 2026Generalizable Sparse-View 3D Reconstruction from Unconstrained Images
4. CVPR 2026Guiding Token-Sparse Diffusion Models
5. CVPR 2026HeSS Head Sensitivity Score for Sparsity Redistribution in VGGT
6. CVPR 2026Improving Sparse Autoencoder with Dynamic Attention
7. CVPR 2026RAPID Reusing Attention Sparsity with Inter-step Adaptation for Efficient Video
8. CVPR 2026Revisiting Pose Sensitivity in Splat-based Computed Tomography under Sparse-view Reconstruction
9. CVPR 2026Sparsity as a Key Unlocking New Insights from Latent Structures
10. CVPR 2026SparVAR Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration
11. CVPR 2026VLM-Pruner Buffering for Spatial Sparsity in an Efficient VLM Centrifugal
12. CVPR 2026When Lines Meet Textures Spatial-Frequency Aligned Diffusion Features for Cross-Sparsity
13. ICLR 2026Composable Sparse Subnetworks via Maximum-Entropy Principle
14. ICLR 2026DIFFSPARSE: ACCELERATING DIFFUSION TRANSFORMERS WITH LEARNED TOKEN SPARSITY
15. ICLR 2026DirMoE: Dirichlet-Routed Mixture of Experts
16. ICLR 2026Doloris: Dual Conditional Diffusion Implicit Bridges with Sparsity Masking Strategy for Unpaired Single-Cell Perturbation Estimation
17. ICLR 2026DSA: Efficient Inference For Video Generation Models via Distributed Sparse Attention
18. ICLR 2026FASA: FREQUENCY-AWARE SPARSE ATTENTION
19. ICLR 2026Hilbert-Guided Sparse Local Attention
20. ICLR 2026Identifiability Challenges in Sparse Linear Ordinary Differential Equations
21. ICLR 2026Implicit Sensing for Fourier Sparse Boolean Functions
22. ICLR 2026Learning Semi-Structured Sparsity for LLMs via Shared and Context-Aware Hypernetwork
23. ICLR 2026LeSTD: LLM Compression via Learning-based Sparse Tensor Decomposition
24. ICLR 2026MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs
25. ICLR 2026Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity
26. ICLR 2026Nasty Adversarial Training: A Probability Sparsity Perspective for Robustness Enhancement
27. ICLR 2026OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework
28. ICLR 2026RAPID$^3$: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer
29. ICLR 2026Robust Training of Neural Networks at Arbitrary Precision and Sparsity
30. ICLR 2026Scaling Attention via Feature Sparsity
31. ICLR 2026SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE Models
32. ICLR 2026SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention
33. ICLR 2026Sparling: End-to-End Spatial Concept Learning via Extremely Sparse Activations
34. ICLR 2026Sparsity Forcing: Reinforcing Token Sparsity of MLLMs
35. ICLR 2026Universal Properties of Activation Sparsity in Modern Large Language Models
36. ICLR 2026vAttention: Verified Sparse Attention via Sampling
37. ICML 2026AdaSplash-2: Faster Differentiable Sparse Attention
38. ICML 2026An Evidential Route to Asymptotic Bayes Optimality under Sparsity
39. ICML 2026AsyncSpade: Efficient Test-Time Scaling with Asynchronous Sparse Decoding
40. ICML 2026Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering
41. ICML 2026Column Thresholding for Sparse Spiked Wigner Models: Improved Signal Strength Requirements
42. ICML 2026DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding
43. ICML 2026Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers
44. ICML 2026Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding
45. ICML 2026FlashSketch: Sketch-Kernel Co-Design for Fast Sparse Sketching on GPUs
46. ICML 2026HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces
47. ICML 2026Incremental Learning of Sparse Attention Patterns in Transformers
48. ICML 2026Lie-Algebraic Acceleration of Neural Koopman Dynamics
49. ICML 2026MACKO: Sparse matrix-vector multiplication for low sparsity
50. ICML 2026Memory-Efficient LLM Training with Dynamic Sparsity: From Stability to Practical Scaling

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。