高效训练论文趋势 2023–2026
Scaling law、MoE、蒸馏与训练效率
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,765 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 112 | 67 | 83 | 84 | 346 |
| 2024 | 20 | 78 | 122 | 80 | 300 |
| 2025 | 190 | 126 | 118 | 82 | 516 |
| 2026 | 177 | 148 | 169 | 109 | 603 |
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 355 篇，第 7 / 8 页
- CVPR 2023Efficient RGB-T Tracking via Cross-Modality Distillation
- CVPR 2023Efficient Robust Principal Component Analysis via Block Krylov Iteration and CUR Decomposition
- CVPR 2023Efficient Scale-Invariant Generator With Column-Row Entangled Pixel Synthesis
- CVPR 2023Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos
- CVPR 2023Efficient Verification of Neural Networks Against LVM-Based Specifications
- CVPR 2023Efficient View Synthesis and 3D-Based Multi-Frame Denoising With Multiplane Feature Representations
- CVPR 2023EfficientViT: Memory Efficient Vision Transformer With Cascaded Group Attention
- CVPR 2023Energy-Efficient Adaptive 3D Sensing
- CVPR 2023expOSE: Accurate Initialization-Free Projective Factorization Using Exponential Regularization
- CVPR 2023Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation
- CVPR 2023FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER
- CVPR 2023FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning
- CVPR 2023FFCV: Accelerating Training by Removing Data Bottlenecks
- CVPR 2023Fine-Tuned CLIP Models Are Efficient Video Learners
- CVPR 2023Four-View Geometry With Unknown Radial Distortion
- CVPR 2023Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge Distillation
- CVPR 2023Generic-to-Specific Distillation of Masked Autoencoders
- CVPR 2023HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes With Iterative Intertwined Regularization
- CVPR 2023Joint Appearance and Motion Learning for Efficient Rolling Shutter Correction
- CVPR 2023LargeKernel3D: Scaling Up Kernels in 3D Sparse CNNs
- CVPR 2023Learning Steerable Function for Efficient Image Resampling
- CVPR 2023LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization
- CVPR 2023Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR
- CVPR 2023Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving
- CVPR 2023Masked Autoencoders Enable Efficient Knowledge Distillers
- CVPR 2023Minimizing the Accumulated Trajectory Error To Improve Dataset Distillation
- CVPR 2023N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution
- CVPR 2023Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation From 2D Supervision
- CVPR 2023Neural Rate Estimator and Unsupervised Learning for Efficient Distributed Image Analytics in Split-DNN Models
- CVPR 2023PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection
- CVPR 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation
- CVPR 2023POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery
- CVPR 2023Progressive Spatio-Temporal Alignment for Efficient Event-Based Motion Estimation
- CVPR 2023ProphNet: Efficient Agent-Centric Motion Forecasting With Anchor-Informed Proposals
- CVPR 2023ProtoCon: Pseudo-Label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-Supervised Learning
- CVPR 2023Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge
- CVPR 2023Q-DETR: An Efficient Low-Bit Quantized Detection Transformer
- CVPR 2023Re-GAN: Data-Efficient GANs Training via Architectural Reconfiguration
- CVPR 2023RelightableHands: Efficient Neural Relighting of Articulated Hand Models
- CVPR 2023Resource-Efficient RGBD Aerial Tracking
- CVPR 2023Samples With Low Loss Curvature Improve Data Efficiency
- CVPR 2023Solving Relaxations of MAP-MRF Problems: Combinatorial In-Face Frank-Wolfe Directions
- CVPR 2023Spider GAN: Leveraging Friendly Neighbors To Accelerate GAN Training
- CVPR 2023Stitchable Neural Networks
- CVPR 2023Structured Sparsity Learning for Efficient Video Super-Resolution
- CVPR 2023Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning
- CVPR 2023Tensor4D: Efficient Neural 4D Decomposition for High-Fidelity Dynamic Reconstruction and Rendering
- CVPR 2023The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection
- CVPR 2023TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers
- CVPR 2023Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查高效训练在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "efficient-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。