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 190 篇，第 2 / 4 页

51. NeurIPS 2025Efficient Fairness-Performance Pareto Front Computation
52. NeurIPS 2025Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning
53. NeurIPS 2025Efficient Kernelized Learning in Polyhedral Games beyond Full Information: From Colonel Blotto to Congestion Games
54. NeurIPS 2025Efficient Large Language Model Inference with Neural Block Linearization
55. NeurIPS 2025Efficient Last-Iterate Convergence in Solving Extensive-Form Games
56. NeurIPS 2025Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling
57. NeurIPS 2025Efficient Multi-modal Large Language Models via Progressive Consistency Distillation
58. NeurIPS 2025Efficient Multimodal Dataset Distillation via Generative Models
59. NeurIPS 2025Efficient PAC Learning for Realizable-Statistic Models via Convex Surrogates
60. NeurIPS 2025Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems
61. NeurIPS 2025Efficient Part-level 3D Object Generation via Dual Volume Packing
62. NeurIPS 2025Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference
63. NeurIPS 2025Efficient RAW Image Deblurring with Adaptive Frequency Modulation
64. NeurIPS 2025Efficient Representativeness-Aware Coreset Selection
65. NeurIPS 2025Efficient semantic uncertainty quantification in language models via diversity-steered sampling
66. NeurIPS 2025Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space
67. NeurIPS 2025Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery
68. NeurIPS 2025Efficient Verified Unlearning For Distillation
69. NeurIPS 2025ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets
70. NeurIPS 2025Emergence and scaling laws in SGD learning of shallow neural networks
71. NeurIPS 2025EventMG: Efficient Multilevel Mamba-Graph Learning for Spatiotemporal Event Representation
72. NeurIPS 2025Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling
73. NeurIPS 2025F-Adapter: Frequency-Adaptive Parameter-Efficient Fine-Tuning in Scientific Machine Learning
74. NeurIPS 2025FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation
75. NeurIPS 2025Fair Minimum Labeling: Efficient Temporal Network Activations for Reachability and Equity
76. NeurIPS 2025FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing
77. NeurIPS 2025FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language Models
78. NeurIPS 2025First Attentions Last: Better Exploiting First Attentions for Efficient Parallel Training
79. NeurIPS 2025FlashBias: Fast Computation of Attention with Bias
80. NeurIPS 2025FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts
81. NeurIPS 2025FraPPE: Fast and Efficient Preference-Based Pure Exploration
82. NeurIPS 2025Frequency-Aware Token Reduction for Efficient Vision Transformer
83. NeurIPS 2025Functional Scaling Laws in Kernel Regression: Loss Dynamics and Learning Rate Schedules
84. NeurIPS 2025GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights
85. NeurIPS 2025Gemstones: A Model Suite for Multi-Faceted Scaling Laws
86. NeurIPS 2025Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update
87. NeurIPS 2025Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts
88. NeurIPS 2025GMV: A Unified and Efficient Graph Multi-View Learning Framework
89. NeurIPS 2025Gradient Multi-Normalization for Efficient LLM Training
90. NeurIPS 2025Group-Level Data Selection for Efficient Pretraining
91. NeurIPS 2025GSPN-2: Efficient Parallel Sequence Modeling
92. NeurIPS 2025Hadamard Test is Sufficient for Efficient Quantum Gradient Estimation with Lie Algebraic Symmetries
93. NeurIPS 2025Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning
94. NeurIPS 2025Hierachical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM
95. NeurIPS 2025HiFC: High-efficiency Flash-based KV Cache Swapping for Scaling LLM Inference
96. NeurIPS 2025HollowFlow: Efficient Sample Likelihood Evaluation using Hollow Message Passing
97. NeurIPS 2025Hybrid Re-matching for Continual Learning with Parameter-Efficient Tuning
98. NeurIPS 2025HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization
99. NeurIPS 2025Hyperbolic Dataset Distillation
100. NeurIPS 2025HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models

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。