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 516 篇，第 2 / 11 页

51. CVPR 2025LoKi: Low-dimensional KAN for Efficient Fine-tuning Image Models
52. CVPR 2025MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Action Anticipation
53. CVPR 2025MEET: Towards Memory-Efficient Temporal Sparse Deep Neural Networks
54. CVPR 2025Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning
55. CVPR 2025MoST: Efficient Monarch Sparse Tuning for 3D Representation Learning
56. CVPR 2025No Pains, More Gains: Recycling Sub-Salient Patches for Efficient High-Resolution Image Recognition
57. CVPR 2025NoT: Federated Unlearning via Weight Negation
58. CVPR 2025NVILA: Efficient Frontier Visual Language Models
59. CVPR 2025Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation
60. CVPR 2025Practical Solutions to the Relative Pose of Three Calibrated Cameras
61. CVPR 2025Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness
62. CVPR 2025Proximal Algorithm Unrolling: Flexible and Efficient Reconstruction Networks for Single-Pixel Imaging
63. CVPR 2025PS-EIP: Robust Photometric Stereo Based on Event Interval Profile
64. CVPR 2025Query Efficient Black-Box Visual Prompting with Subspace Learning
65. CVPR 2025Rethinking Token Reduction with Parameter-Efficient Fine-Tuning in ViT for Pixel-Level Tasks
66. CVPR 2025RivuletMLP: An MLP-based Architecture for Efficient Compressed Video Quality Enhancement
67. CVPR 2025Sample- and Parameter-Efficient Auto-Regressive Image Models
68. CVPR 2025Scale Efficient Training for Large Datasets
69. CVPR 2025Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentation
70. CVPR 2025SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation
71. CVPR 2025Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch
72. CVPR 2025SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer
73. CVPR 2025Spatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecasting
74. CVPR 2025Style Quantization for Data-Efficient GAN Training
75. CVPR 2025TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion
76. CVPR 2025TADFormer: Task-Adaptive Dynamic TransFormer for Efficient Multi-Task Learning
77. CVPR 2025Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding
78. CVPR 2025Towards Efficient Foundation Model for Zero-shot Amodal Segmentation
79. CVPR 2025Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory
80. CVPR 2025Trajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSM
81. CVPR 2025Two is Better than One: Efficient Ensemble Defense for Robust and Compact Models
82. CVPR 2025ViKIENet: Towards Efficient 3D Object Detection with Virtual Key Instance Enhanced Network
83. ICLR 2025(Mis)Fitting Scaling Laws: A Survey of Scaling Law Fitting Techniques in Deep Learning
84. ICLR 2025$\text{D}_{2}\text{O}$: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models
85. ICLR 2025A Graph Enhanced Symbolic Discovery Framework For Efficient Logic Optimization
86. ICLR 2025A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts
87. ICLR 2025A Quantum Circuit-Based Compression Perspective for Parameter-Efficient Learning
88. ICLR 2025ADAPT: Attentive Self-Distillation and Dual-Decoder Prediction Fusion for Continual Panoptic Segmentation
89. ICLR 2025Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws
90. ICLR 2025ADePT: Adaptive Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning
91. ICLR 2025ANaGRAM: A Natural Gradient Relative to Adapted Model for efficient PINNs learning
92. ICLR 2025Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator
93. ICLR 2025Breaking Neural Network Scaling Laws with Modularity
94. ICLR 2025Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLMs with Semantic Space
95. ICLR 2025Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling
96. ICLR 2025CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences
97. ICLR 2025CheapNet: Cross-attention on Hierarchical representations for Efficient protein-ligand binding Affinity Prediction
98. ICLR 2025CipherPrune: Efficient and Scalable Private Transformer Inference
99. ICLR 2025Closed-Form Merging of Parameter-Efficient Modules for Federated Continual Learning
100. ICLR 2025COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training

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。