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 122 篇，第 2 / 3 页

51. ICML 2024Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits
52. ICML 2024Fast Decision Boundary based Out-of-Distribution Detector
53. ICML 2024Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training
54. ICML 2024FedBAT: Communication-Efficient Federated Learning via Learnable Binarization
55. ICML 2024FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models
56. ICML 2024Flextron: Many-in-One Flexible Large Language Model
57. ICML 2024Gated Linear Attention Transformers with Hardware-Efficient Training
58. ICML 2024GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
59. ICML 2024Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference
60. ICML 2024Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization
61. ICML 2024Graph Distillation with Eigenbasis Matching
62. ICML 2024GroupCover: A Secure, Efficient and Scalable Inference Framework for On-device Model Protection based on TEEs
63. ICML 2024InferCept: Efficient Intercept Support for Augmented Large Language Model Inference
64. ICML 2024InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models
65. ICML 2024Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization
66. ICML 2024Knowledge Distillation with Auxiliary Variable
67. ICML 2024Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs
68. ICML 2024Learning-Efficient Yet Generalizable Collaborative Filtering for Item Recommendation
69. ICML 2024Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference
70. ICML 2024Measuring Stochastic Data Complexity with Boltzmann Influence Functions
71. ICML 2024Memory Efficient Neural Processes via Constant Memory Attention Block
72. ICML 2024MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data Utilization
73. ICML 2024Multi-Region Markovian Gaussian Process: An Efficient Method to Discover Directional Communications Across Multiple Brain Regions
74. ICML 2024Navigating Scaling Laws: Compute Optimality in Adaptive Model Training
75. ICML 2024Nonparametric Teaching of Implicit Neural Representations
76. ICML 2024On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis
77. ICML 2024Online Cascade Learning for Efficient Inference over Streams
78. ICML 2024Orthogonal Bootstrap: Efficient Simulation of Input Uncertainty
79. ICML 2024Outlier-Efficient Hopfield Layers for Large Transformer-Based Models
80. ICML 2024Outlier-robust Kalman Filtering through Generalised Bayes
81. ICML 2024Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation
82. ICML 2024Parameter-Efficient Fine-Tuning with Controls
83. ICML 2024Parameter-Efficient Fine-Tuning with Discrete Fourier Transform
84. ICML 2024Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized Systems
85. ICML 2024Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses
86. ICML 2024Quality-Diversity with Limited Resources
87. ICML 2024QUEST: Query-Aware Sparsity for Efficient Long-Context LLM Inference
88. ICML 2024Random Masking Finds Winning Tickets for Parameter Efficient Fine-tuning
89. ICML 2024Ranking-based Client Imitation Selection for Efficient Federated Learning
90. ICML 2024Replicable Learning of Large-Margin Halfspaces
91. ICML 2024REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates
92. ICML 2024Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
93. ICML 2024Robust Yet Efficient Conformal Prediction Sets
94. ICML 2024Saliency strikes back: How filtering out high frequencies improves white-box explanations
95. ICML 2024Scalable AI Safety via Doubly-Efficient Debate
96. ICML 2024Scalable and Flexible Causal Discovery with an Efficient Test for Adjacency
97. ICML 2024Scaling Beyond the GPU Memory Limit for Large Mixture-of-Experts Model Training
98. ICML 2024Scaling Down Deep Learning with MNIST-1D
99. ICML 2024Scaling Laws for Fine-Grained Mixture of Experts
100. ICML 2024Scaling Laws for the Value of Individual Data Points in Machine Learning

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。