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 2 / 2 页

  1. NeurIPS 2024Adaptive Layer Sparsity for Large Language Models via Activation Correlation Assessment
  2. NeurIPS 2024AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
  3. NeurIPS 2024Block Sparse Bayesian Learning: A Diversified Scheme
  4. NeurIPS 2024CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks
  5. NeurIPS 2024Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models
  6. NeurIPS 2024ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration
  7. NeurIPS 2024Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations
  8. NeurIPS 2024How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective
  9. NeurIPS 2024Improving Decision Sparsity
  10. NeurIPS 2024Learn To be Efficient: Build Structured Sparsity in Large Language Models
  11. NeurIPS 2024Learning from Highly Sparse Spatio-temporal Data
  12. NeurIPS 2024MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models
  13. NeurIPS 2024Navigating Extremes: Dynamic Sparsity in Large Output Spaces
  14. NeurIPS 2024Nesterov acceleration despite very noisy gradients
  15. NeurIPS 2024Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees
  16. NeurIPS 2024On the Sparsity of the Strong Lottery Ticket Hypothesis
  17. NeurIPS 2024S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training
  18. NeurIPS 2024Solving Sparse \& High-Dimensional-Output Regression via Compression
  19. NeurIPS 2024Sparse maximal update parameterization: A holistic approach to sparse training dynamics
  20. NeurIPS 2024Sparsity-Agnostic Linear Bandits with Adaptive Adversaries
  21. NeurIPS 2023Canonical normalizing flows for manifold learning
  22. NeurIPS 2023Double Randomized Underdamped Langevin with Dimension-Independent Convergence Guarantee
  23. NeurIPS 2023Dynamic Sparsity Is Channel-Level Sparsity Learner
  24. NeurIPS 2023On the Identifiability of Sparse ICA without Assuming Non-Gaussianity
  25. NeurIPS 2023Penalising the biases in norm regularisation enforces sparsity
  26. NeurIPS 2023Robust Model Reasoning and Fitting via Dual Sparsity Pursuit
  27. NeurIPS 2023Sparsity-Preserving Differentially Private Training of Large Embedding Models
  28. NeurIPS 2023SUBP: Soft Uniform Block Pruning for 1$\times$N Sparse CNNs Multithreading Acceleration
  29. NeurIPS 2023Tanh Works Better with Asymmetry
  30. NeurIPS 2023Towards Data-Agnostic Pruning At Initialization: What Makes a Good Sparse Mask?

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