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 64 篇，第 1 / 2 页

1. CVPR 2025CASP: Compression of Large Multimodal Models Based on Attention Sparsity
2. CVPR 2025ICP: Immediate Compensation Pruning for Mid-to-high Sparsity
3. CVPR 2025MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds
4. CVPR 2025S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splatting
5. CVPR 2025SINR: Sparsity Driven Compressed Implicit Neural Representations
6. ICLR 2025Beyond Worst-Case Dimensionality Reduction for Sparse Vectors
7. ICLR 2025Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries
8. ICLR 2025DPaI: Differentiable Pruning at Initialization with Node-Path Balance Principle
9. ICLR 2025Dynamic Low-Rank Sparse Adaptation for Large Language Models
10. ICLR 2025Efficient Sparse PCA via Block-Diagonalization
11. ICLR 2025From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency
12. ICLR 2025Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error
13. ICLR 2025R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
14. ICLR 2025ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
15. ICLR 2025RTop-K: Ultra-Fast Row-Wise Top-K Selection for Neural Network Acceleration on GPUs
16. ICLR 2025Schur's Positive-Definite Network: Deep Learning in the SPD cone with structure
17. ICLR 2025Semantic Aware Representation Learning for Lifelong Learning
18. ICLR 2025Training-Free Activation Sparsity in Large Language Models
19. ICLR 2025Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization
20. ICLR 2025VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration
21. ICLR 2025Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity
22. ICML 2025Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity
23. ICML 2025AdaSplash: Adaptive Sparse Flash Attention
24. ICML 2025BAME: Block-Aware Mask Evolution for Efficient N:M Sparse Training
25. ICML 2025Be a Goldfish: Forgetting Bad Conditioning in Sparse Linear Regression via Variational Autoencoders
26. ICML 2025COGNATE: Acceleration of Sparse Tensor Programs on Emerging Hardware using Transfer Learning
27. ICML 2025CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models
28. ICML 2025Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective
29. ICML 2025Dynamic Sparse Training of Diagonally Sparse Networks
30. ICML 2025Fast Inference with Kronecker-Sparse Matrices
31. ICML 2025FlashTP: Fused, Sparsity-Aware Tensor Product for Machine Learning Interatomic Potentials
32. ICML 2025Grokking Beyond the Euclidean Norm of Model Parameters
33. ICML 2025Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries
34. ICML 2025Metadata Conditioning Accelerates Language Model Pre-training
35. ICML 2025Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning
36. ICML 2025Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models
37. ICML 2025Position: A Theory of Deep Learning Must Include Compositional Sparsity
38. ICML 2025PROXSPARSE: REGULARIZED LEARNING OF SEMI-STRUCTURED SPARSITY MASKS FOR PRETRAINED LLMS
39. ICML 2025SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
40. ICML 2025Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
41. ICML 2025Sparsing Law: Towards Large Language Models with Greater Activation Sparsity
42. ICML 2025When Dynamic Data Selection Meets Data Augmentation: Achieving Enhanced Training Acceleration
43. ICML 2025XAttention: Block Sparse Attention with Antidiagonal Scoring
44. NeurIPS 2025Bilevel Network Learning via Hierarchically Structured Sparsity
45. NeurIPS 2025Bivariate Matrix-valued Linear Regression (BMLR): Finite-sample performance under Identifiability and Sparsity Assumptions
46. NeurIPS 2025CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
47. NeurIPS 2025Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization
48. NeurIPS 2025DuoGPT: Training-free Dual Sparsity through Activation-aware Pruning in LLMs
49. NeurIPS 2025Exploiting Dynamic Sparsity in Einsum
50. NeurIPS 2025Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks

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。