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 72 篇，第 1 / 2 页

  1. ICLR 2026Composable Sparse Subnetworks via Maximum-Entropy Principle
  2. ICLR 2026DIFFSPARSE: ACCELERATING DIFFUSION TRANSFORMERS WITH LEARNED TOKEN SPARSITY
  3. ICLR 2026DirMoE: Dirichlet-Routed Mixture of Experts
  4. ICLR 2026Doloris: Dual Conditional Diffusion Implicit Bridges with Sparsity Masking Strategy for Unpaired Single-Cell Perturbation Estimation
  5. ICLR 2026DSA: Efficient Inference For Video Generation Models via Distributed Sparse Attention
  6. ICLR 2026FASA: FREQUENCY-AWARE SPARSE ATTENTION
  7. ICLR 2026Hilbert-Guided Sparse Local Attention
  8. ICLR 2026Identifiability Challenges in Sparse Linear Ordinary Differential Equations
  9. ICLR 2026Implicit Sensing for Fourier Sparse Boolean Functions
  10. ICLR 2026Learning Semi-Structured Sparsity for LLMs via Shared and Context-Aware Hypernetwork
  11. ICLR 2026LeSTD: LLM Compression via Learning-based Sparse Tensor Decomposition
  12. ICLR 2026MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs
  13. ICLR 2026Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity
  14. ICLR 2026Nasty Adversarial Training: A Probability Sparsity Perspective for Robustness Enhancement
  15. ICLR 2026OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework
  16. ICLR 2026RAPID$^3$: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer
  17. ICLR 2026Robust Training of Neural Networks at Arbitrary Precision and Sparsity
  18. ICLR 2026Scaling Attention via Feature Sparsity
  19. ICLR 2026SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE Models
  20. ICLR 2026SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention
  21. ICLR 2026Sparling: End-to-End Spatial Concept Learning via Extremely Sparse Activations
  22. ICLR 2026Sparsity Forcing: Reinforcing Token Sparsity of MLLMs
  23. ICLR 2026Universal Properties of Activation Sparsity in Modern Large Language Models
  24. ICLR 2026vAttention: Verified Sparse Attention via Sampling
  25. ICLR 2025Beyond Worst-Case Dimensionality Reduction for Sparse Vectors
  26. ICLR 2025Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries
  27. ICLR 2025DPaI: Differentiable Pruning at Initialization with Node-Path Balance Principle
  28. ICLR 2025Dynamic Low-Rank Sparse Adaptation for Large Language Models
  29. ICLR 2025Efficient Sparse PCA via Block-Diagonalization
  30. ICLR 2025From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency
  31. ICLR 2025Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error
  32. ICLR 2025R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
  33. ICLR 2025ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
  34. ICLR 2025RTop-K: Ultra-Fast Row-Wise Top-K Selection for Neural Network Acceleration on GPUs
  35. ICLR 2025Schur's Positive-Definite Network: Deep Learning in the SPD cone with structure
  36. ICLR 2025Semantic Aware Representation Learning for Lifelong Learning
  37. ICLR 2025Training-Free Activation Sparsity in Large Language Models
  38. ICLR 2025Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization
  39. ICLR 2025VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration
  40. ICLR 2025Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity
  41. ICLR 2024Adaptive Sharpness-Aware Pruning for Robust Sparse Networks
  42. ICLR 2024Balancing Act: Constraining Disparate Impact in Sparse Models
  43. ICLR 2024DEEP NEURAL NETWORK INITIALIZATION WITH SPARSITY INDUCING ACTIVATIONS
  44. ICLR 2024Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs
  45. ICLR 2024Dynamic Sparse Training with Structured Sparsity
  46. ICLR 2024ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
  47. ICLR 2024SAS: Structured Activation Sparsification
  48. ICLR 2024Sparsistency for inverse optimal transport
  49. ICLR 2024SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
  50. ICLR 2024Training Bayesian Neural Networks with Sparse Subspace Variational Inference

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