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 112 篇，第 2 / 3 页

51. NeurIPS 2023FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations
52. NeurIPS 2023Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations
53. NeurIPS 2023GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients
54. NeurIPS 2023H3T: Efficient Integration of Memory Optimization and Parallelism for Large-scale Transformer Training
55. NeurIPS 2023How2comm: Communication-Efficient and Collaboration-Pragmatic Multi-Agent Perception
56. NeurIPS 2023Hybrid Search for Efficient Planning with Completeness Guarantees
57. NeurIPS 2023Label Robust and Differentially Private Linear Regression: Computational and Statistical Efficiency
58. NeurIPS 2023Language Semantic Graph Guided Data-Efficient Learning
59. NeurIPS 2023Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations
60. NeurIPS 2023Mask Propagation for Efficient Video Semantic Segmentation
61. NeurIPS 2023Maximum Independent Set: Self-Training through Dynamic Programming
62. NeurIPS 2023MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers
63. NeurIPS 2023Memory Efficient Optimizers with 4-bit States
64. NeurIPS 2023MGDD: A Meta Generator for Fast Dataset Distillation
65. NeurIPS 2023MixFormerV2: Efficient Fully Transformer Tracking
66. NeurIPS 2023MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining
67. NeurIPS 2023Multiplication-Free Transformer Training via Piecewise Affine Operations
68. NeurIPS 2023NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks
69. NeurIPS 2023Neural Priming for Sample-Efficient Adaptation
70. NeurIPS 2023NICE: NoIse-modulated Consistency rEgularization for Data-Efficient GANs
71. NeurIPS 2023No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models
72. NeurIPS 2023On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
73. NeurIPS 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models
74. NeurIPS 2023Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
75. NeurIPS 2023PDP: Parameter-free Differentiable Pruning is All You Need
76. NeurIPS 2023Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources
77. NeurIPS 2023Pre-RMSNorm and Pre-CRMSNorm Transformers: Equivalent and Efficient Pre-LN Transformers
78. NeurIPS 2023Progressive Ensemble Distillation: Building Ensembles for Efficient Inference
79. NeurIPS 2023QLoRA: Efficient Finetuning of Quantized LLMs
80. NeurIPS 2023RangePerception: Taming LiDAR Range View for Efficient and Accurate 3D Object Detection
81. NeurIPS 2023ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
82. NeurIPS 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting
83. NeurIPS 2023RETVec: Resilient and Efficient Text Vectorizer
84. NeurIPS 2023Reusing Pretrained Models by Multi-linear Operators for Efficient Training
85. NeurIPS 2023Sample-efficient Multi-objective Molecular Optimization with GFlowNets
86. NeurIPS 2023ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection
87. NeurIPS 2023Scaling Data-Constrained Language Models
88. NeurIPS 2023ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer
89. NeurIPS 2023SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling
90. NeurIPS 2023SLaM: Student-Label Mixing for Distillation with Unlabeled Examples
91. NeurIPS 2023Slimmed Asymmetrical Contrastive Learning and Cross Distillation for Lightweight Model Training
92. NeurIPS 2023Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks
93. NeurIPS 2023Sparse Modular Activation for Efficient Sequence Modeling
94. NeurIPS 2023SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networks
95. NeurIPS 2023Sparsity-Preserving Differentially Private Training of Large Embedding Models
96. NeurIPS 2023Speculative Decoding with Big Little Decoder
97. NeurIPS 2023Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective
98. NeurIPS 2023Stable Nonconvex-Nonconcave Training via Linear Interpolation
99. NeurIPS 2023Text Alignment Is An Efficient Unified Model for Massive NLP Tasks
100. NeurIPS 2023To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis

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。