稀疏加速论文趋势 2023–2026

稀疏算子

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 260 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

稀疏加速论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20231022111154
2024201018553
2025211622564
20262924241289

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

全部稀疏加速论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 80 篇，第 1 / 2 页

  1. NeurIPS 2026AC/DC on a Budget -- Alternating Sparse Phases
  2. NeurIPS 2026Asymmetric Scaling Laws from Sparse Features
  3. NeurIPS 2026Attribute-Efficient Learning of Sparse Halfspaces with Constant Malicious Noise Rate
  4. NeurIPS 2026Beyond Masked Sparsity: SNACK Enables Truly Sparse Neural Networks on GPU
  5. NeurIPS 2026Cannistraci-Hebb Channel-wise Dynamic Sparse Training of Convolutional Neural Networks with Contextual Modulation
  6. NeurIPS 2026Coarse-to-Fine 3D MRI Reconstruction via Resolution-Agnostic Neural Operators
  7. NeurIPS 2026Colour me shocked: Exact Molecular Hessians from MLIPs in O(N) time using sparse differentiation!
  8. NeurIPS 2026Contribution-Aware Structured Sparsity for Model Merging
  9. NeurIPS 2026Direct Acceleration of Stochastic Root-Finding Without Variance Reduction and Regularization
  10. NeurIPS 2026Distribution Free Fourier Sparsity Testing
  11. NeurIPS 2026Effectiveness of Curriculum Learning Depends on Reward Sparsity and Competing Optima
  12. NeurIPS 2026Efficient Fine-Tuning for Structured Sparsity Under Group Repartitioning
  13. NeurIPS 2026Flow Matching from Viewpoint of Proximal Operators
  14. NeurIPS 2026Inference-time Alignment via Sparse Junction Steering
  15. NeurIPS 2026Intrinsically Interpretable Attention via Sparse Post-Training
  16. NeurIPS 2026Inverting Retargeting: Humanoid Datasets Remember Their Operators
  17. NeurIPS 2026Learning Event-to-Field Operators Without Interpolation
  18. NeurIPS 2026Long-Context Language Models Require Extreme Sparsity in Context Dimension
  19. NeurIPS 2026On the Sparsity of Direct Preference Optimization: Weight Disentanglement in the NTK Regime
  20. NeurIPS 2026On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning
  21. NeurIPS 2026OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
  22. NeurIPS 2026Perfect Parallelization in Mini-Batch SGD with Classical Momentum Acceleration
  23. NeurIPS 2026Posterior Contraction Rates for sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces
  24. NeurIPS 2026Sparse blind deconvolution via thresholded Wirtinger flow
  25. NeurIPS 2026Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
  26. NeurIPS 2026Sparse Sum-of-Squares Layers for Certified Learning
  27. NeurIPS 2026SVDP: Training-Free Contextual Sparsity Predictors for Fast LLM Inference
  28. NeurIPS 2026The Sparsity Whisperer
  29. NeurIPS 2026Transferable SCF-Acceleration through Solver-Aligned Initialization Learning
  30. NeurIPS 2025Bilevel Network Learning via Hierarchically Structured Sparsity
  31. NeurIPS 2025Bivariate Matrix-valued Linear Regression (BMLR): Finite-sample performance under Identifiability and Sparsity Assumptions
  32. NeurIPS 2025CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
  33. NeurIPS 2025Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization
  34. NeurIPS 2025DuoGPT: Training-free Dual Sparsity through Activation-aware Pruning in LLMs
  35. NeurIPS 2025Exploiting Dynamic Sparsity in Einsum
  36. NeurIPS 2025Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks
  37. NeurIPS 2025Masked Gated Linear Unit
  38. NeurIPS 2025MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE
  39. NeurIPS 2025MUSTAFAR: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference
  40. NeurIPS 2025PermLLM: Learnable Channel Permutation for N:M Sparse Large Language Models
  41. NeurIPS 2025Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity
  42. NeurIPS 2025Price of Parsimony: Complexity of Fourier Sparsity Testing
  43. NeurIPS 2025Sign-In to the Lottery: Reparameterizing Sparse Training
  44. NeurIPS 2025Spark Transformer: Reactivating Sparsity in Transformer FFN and Attention
  45. NeurIPS 2025Stochastic Shortest Path with Sparse Adversarial Costs
  46. NeurIPS 2025The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements
  47. NeurIPS 2025TSENOR: Highly-Efficient Algorithm for Finding Transposable N:M Sparse Masks
  48. NeurIPS 2025Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning
  49. NeurIPS 2025Týr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization
  50. NeurIPS 2025You Only Spectralize Once: Taking a Spectral Detour to Accelerate Graph Neural Network

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查稀疏加速在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "sparsity-acceleration"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「硬件与编译」下的其他主题