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 82 篇，第 2 / 2 页
- CVPR 2025LoKi: Low-dimensional KAN for Efficient Fine-tuning Image Models
- CVPR 2025MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Action Anticipation
- CVPR 2025MEET: Towards Memory-Efficient Temporal Sparse Deep Neural Networks
- CVPR 2025Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning
- CVPR 2025MoST: Efficient Monarch Sparse Tuning for 3D Representation Learning
- CVPR 2025No Pains, More Gains: Recycling Sub-Salient Patches for Efficient High-Resolution Image Recognition
- CVPR 2025NoT: Federated Unlearning via Weight Negation
- CVPR 2025NVILA: Efficient Frontier Visual Language Models
- CVPR 2025Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation
- CVPR 2025Practical Solutions to the Relative Pose of Three Calibrated Cameras
- CVPR 2025Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness
- CVPR 2025Proximal Algorithm Unrolling: Flexible and Efficient Reconstruction Networks for Single-Pixel Imaging
- CVPR 2025PS-EIP: Robust Photometric Stereo Based on Event Interval Profile
- CVPR 2025Query Efficient Black-Box Visual Prompting with Subspace Learning
- CVPR 2025Rethinking Token Reduction with Parameter-Efficient Fine-Tuning in ViT for Pixel-Level Tasks
- CVPR 2025RivuletMLP: An MLP-based Architecture for Efficient Compressed Video Quality Enhancement
- CVPR 2025Sample- and Parameter-Efficient Auto-Regressive Image Models
- CVPR 2025Scale Efficient Training for Large Datasets
- CVPR 2025Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentation
- CVPR 2025SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation
- CVPR 2025Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch
- CVPR 2025SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer
- CVPR 2025Spatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecasting
- CVPR 2025Style Quantization for Data-Efficient GAN Training
- CVPR 2025TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion
- CVPR 2025TADFormer: Task-Adaptive Dynamic TransFormer for Efficient Multi-Task Learning
- CVPR 2025Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding
- CVPR 2025Towards Efficient Foundation Model for Zero-shot Amodal Segmentation
- CVPR 2025Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory
- CVPR 2025Trajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSM
- CVPR 2025Two is Better than One: Efficient Ensemble Defense for Robust and Compact Models
- CVPR 2025ViKIENet: Towards Efficient 3D Object Detection with Virtual Key Instance Enhanced Network
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。