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 80 篇，第 2 / 2 页

51. CVPR 2024MCNet: Rethinking the Core Ingredients for Accurate and Efficient Homography Estimation
52. CVPR 2024MS-DETR: Efficient DETR Training with Mixed Supervision
53. CVPR 2024NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation
54. CVPR 2024On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm
55. CVPR 2024Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model
56. CVPR 2024PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution
57. CVPR 2024PEM: Prototype-based Efficient MaskFormer for Image Segmentation
58. CVPR 2024PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees
59. CVPR 2024PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild
60. CVPR 2024Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network
61. CVPR 2024Querying as Prompt: Parameter-Efficient Learning for Multimodal Language Model
62. CVPR 2024Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization
63. CVPR 2024Resource-Efficient Transformer Pruning for Finetuning of Large Models
64. CVPR 2024Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples
65. CVPR 2024S2MVTC: a Simple yet Efficient Scalable Multi-View Tensor Clustering
66. CVPR 2024Scalable 3D Registration via Truncated Entry-wise Absolute Residuals
67. CVPR 2024Scaled Decoupled Distillation
68. CVPR 2024Scaling Laws of Synthetic Images for Model Training ... for Now
69. CVPR 2024SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation
70. CVPR 2024Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors
71. CVPR 2024SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design
72. CVPR 2024SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction
73. CVPR 2024Structured Model Probing: Empowering Efficient Transfer Learning by Structured Regularization
74. CVPR 2024SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective
75. CVPR 2024Teeth-SEG: An Efficient Instance Segmentation Framework for Orthodontic Treatment based on Multi-Scale Aggregation and Anthropic Prior Knowledge
76. CVPR 2024Time- Memory- and Parameter-Efficient Visual Adaptation
77. CVPR 2024Time-Efficient Light-Field Acquisition Using Coded Aperture and Events
78. CVPR 2024Towards Efficient Replay in Federated Incremental Learning
79. CVPR 2024UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory
80. CVPR 2024VkD: Improving Knowledge Distillation using Orthogonal Projections

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。