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 1,765 篇，第 32 / 36 页
- ICLR 2023Parameter-Efficient Fine-Tuning Design Spaces
- ICLR 2023PASHA: Efficient HPO and NAS with Progressive Resource Allocation
- ICLR 2023PiFold: Toward effective and efficient protein inverse folding
- ICLR 2023Reparameterization through Spatial Gradient Scaling
- ICLR 2023Scalable and Equivariant Spherical CNNs by Discrete-Continuous (DISCO) Convolutions
- ICLR 2023SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency
- ICLR 2023Scaling Forward Gradient With Local Losses
- ICLR 2023Scaling Up Probabilistic Circuits by Latent Variable Distillation
- ICLR 2023SCoMoE: Efficient Mixtures of Experts with Structured Communication
- ICLR 2023Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning
- ICLR 2023SmartFRZ: An Efficient Training Framework using Attention-Based Layer Freezing
- ICLR 2023Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers
- ICLR 2023Sparse Random Networks for Communication-Efficient Federated Learning
- ICLR 2023Spherical Sliced-Wasserstein
- ICLR 2023Statistical Efficiency of Score Matching: The View from Isoperimetry
- ICLR 2023Teacher Guided Training: An Efficient Framework for Knowledge Transfer
- ICLR 2023The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes
- ICLR 2023Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions
- ICLR 2023Treeformer: Dense Gradient Trees for Efficient Attention Computation
- ICLR 2023Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction
- ICML 2023Auxiliary Modality Learning with Generalized Curriculum Distillation
- ICML 2023BEATs: Audio Pre-Training with Acoustic Tokenizers
- ICML 2023Bi-directional Masks for Efficient N:M Sparse Training
- ICML 2023Bigger, Better, Faster: Human-level Atari with human-level efficiency
- ICML 2023Brainformers: Trading Simplicity for Efficiency
- ICML 2023Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation
- ICML 2023Constrained Efficient Global Optimization of Expensive Black-box Functions
- ICML 2023Cramming: Training a Language Model on a single GPU in one day.
- ICML 2023Data Efficient Neural Scaling Law via Model Reusing
- ICML 2023Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the Least
- ICML 2023Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value
- ICML 2023Dataset Distillation with Convexified Implicit Gradients
- ICML 2023Decoding Layer Saliency in Language Transformers
- ICML 2023Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time
- ICML 2023DIVISION: Memory Efficient Training via Dual Activation Precision
- ICML 2023dugMatting: Decomposed-Uncertainty-Guided Matting
- ICML 2023Effective and Efficient Structural Inference with Reservoir Computing
- ICML 2023Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling
- ICML 2023Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian
- ICML 2023Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction
- ICML 2023Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration
- ICML 2023Efficient displacement convex optimization with particle gradient descent
- ICML 2023Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming
- ICML 2023Efficient List-Decodable Regression using Batches
- ICML 2023Efficient Parametric Approximations of Neural Network Function Space Distance
- ICML 2023Efficient Personalized Federated Learning via Sparse Model-Adaptation
- ICML 2023Efficient preconditioned stochastic gradient descent for estimation in latent variable models
- ICML 2023Efficient Quantum Algorithms for Quantum Optimal Control
- ICML 2023Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation
- ICML 2023Efficient RL via Disentangled Environment and Agent Representations
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。