高效训练论文趋势 2023–2026

主要结论

• 高效训练论文从 2023 年的 346 篇增长到 2026 年的 603 篇，三年间扩大到约 1.7 倍。
• NeurIPS 是发高效训练论文最多的会议，2023–2026 年共 499 篇，占四个会议总量的 28%。
• 交叉方向里涨得最快的是深度学习 · large language models：同时属于两个主题的论文从 2023 年的 6 篇增至 2026 年的 50 篇。
• 在「效率与系统」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的硬件协同是 4.4 倍，高效训练是 1.7 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 2026Adaptive Residual Quantization for Memory-Efficient Temporal Action Segmentation
• ICML 2026A Geometry-Aware Efficient Algorithm for Compositional Entropic Risk Minimization
• ICLR 2026An Efficient SE(p)-Invariant Transport Metric Driven by Polar Transport Discrepancy-based Representation
• CVPR 2026A Bit is All You Need Efficient Video Capture via
• NeurIPS 20254DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming
• ICML 2025A Sample Efficient Conditional Independence Test in the Presence of Discretization
• ICLR 2025Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator
• CVPR 2025Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation
• NeurIPS 2024$\texttt{dattri}$: A Library for Efficient Data Attribution
• ICML 2024A fast algorithm to simulate nonlinear resistive networks
• ICLR 2024Dictionary Contrastive Learning for Efficient Local Supervision without Auxiliary Networks
• CVPR 2024Deep-TROJ: An Inference Stage Trojan Insertion Algorithm through Efficient Weight Replacement Attack
• NeurIPS 2023Alternating Updates for Efficient Transformers
• ICML 2023Auxiliary Modality Learning with Generalized Curriculum Distillation
• ICLR 2023A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning
• CVPR 2023A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization
• NeurIPS 2026Advanced Routing as Regularization Allocation for Efficient Diffusion Transformer Training
• ICML 2026Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance
• ICLR 2026AQER: A Scalable and Efficient Data Loader for Digital Quantum Computers
• CVPR 2026Adaptive Bayesian Early-Exit Networks for Efficient Non-Transferable Learning

全部高效训练论文

共 83 篇，第 2 / 2 页

51. ICML 2023On the convergence of the MLE as an estimator of the learning rate in the Exp3 algorithm
52. ICML 2023Optimal Rates and Efficient Algorithms for Online Bayesian Persuasion
53. ICML 2023Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks
54. ICML 2023Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games
55. ICML 2023PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search
56. ICML 2023Probabilistic Categorical Adversarial Attack and Adversarial Training
57. ICML 2023Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning
58. ICML 2023Provable Data Subset Selection For Efficient Neural Networks Training
59. ICML 2023Provably and Practically Efficient Neural Contextual Bandits
60. ICML 2023Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs
61. ICML 2023Revisiting Data-Free Knowledge Distillation with Poisoned Teachers
62. ICML 2023Rockmate: an Efficient, Fast, Automatic and Generic Tool for Re-materialization in PyTorch
63. ICML 2023Scaling Laws for Multilingual Neural Machine Translation
64. ICML 2023Scaling Spherical CNNs
65. ICML 2023Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory
66. ICML 2023Semiparametrically Efficient Off-Policy Evaluation in Linear Markov Decision Processes
67. ICML 2023Simple Hardware-Efficient Long Convolutions for Sequence Modeling
68. ICML 2023Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability
69. ICML 2023SLAMB: Accelerated Large Batch Training with Sparse Communication
70. ICML 2023SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
71. ICML 2023SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks at the Edge
72. ICML 2023SpotEM: Efficient Video Search for Episodic Memory
73. ICML 2023Stabilizing GANs' Training with Brownian Motion Controller
74. ICML 2023SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient
75. ICML 2023TAN Without a Burn: Scaling Laws of DP-SGD
76. ICML 2023The case for 4-bit precision: k-bit Inference Scaling Laws
77. ICML 2023Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks
78. ICML 2023Towards Understanding and Improving GFlowNet Training
79. ICML 2023Training Normalizing Flows from Dependent Data
80. ICML 2023Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias
81. ICML 2023Unit Scaling: Out-of-the-Box Low-Precision Training
82. ICML 2023Why Is Public Pretraining Necessary for Private Model Training?
83. ICML 2023Why Random Pruning Is All We Need to Start Sparse

常见问题

2023–2026 年四大会议一共有多少篇高效训练论文？

共 1,765 篇，按年份分别是 2023 年 346 篇、2024 年 300 篇、2025 年 516 篇、2026 年 603 篇。

NeurIPS 2026 有多少篇高效训练论文？

NeurIPS 2026 有 177 篇高效训练论文，上一届是 190 篇。

ICLR 2026 有多少篇高效训练论文？

ICLR 2026 有 148 篇高效训练论文，上一届是 126 篇。

ICML 2026 有多少篇高效训练论文？

ICML 2026 有 169 篇高效训练论文，上一届是 118 篇。

CVPR 2026 有多少篇高效训练论文？

CVPR 2026 有 109 篇高效训练论文，上一届是 82 篇。

哪个会议的高效训练论文最多？

NeurIPS，2023–2026 年共 499 篇。