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 33 / 36 页
- ICML 2023Efficient Sequence Transduction by Jointly Predicting Tokens and Durations
- ICML 2023Efficient Training of Language Models using Few-Shot Learning
- ICML 2023ELSA: Efficient Label Shift Adaptation through the Lens of Semiparametric Models
- ICML 2023Forget Unlearning: Towards True Data-Deletion in Machine Learning
- ICML 2023Fourmer: An Efficient Global Modeling Paradigm for Image Restoration
- ICML 2023GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks
- ICML 2023Generalized-Smooth Nonconvex Optimization is As Efficient As Smooth Nonconvex Optimization
- ICML 2023HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption
- ICML 2023Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction
- ICML 2023JAWS-X: Addressing Efficiency Bottlenecks of Conformal Prediction Under Standard and Feedback Covariate Shift
- ICML 2023Label differential privacy and private training data release
- ICML 2023Learn to Accumulate Evidence from All Training Samples: Theory and Practice
- ICML 2023LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning
- ICML 2023Linkless Link Prediction via Relational Distillation
- ICML 2023Lowering the Pre-training Tax for Gradient-based Subset Training: A Lightweight Distributed Pre-Training Toolkit
- ICML 2023Margin-based sampling in high dimensions: When being active is less efficient than staying passive
- ICML 2023Moccasin: Efficient Tensor Rematerialization for Neural Networks
- ICML 2023Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions
- ICML 2023Multi-Objective Population Based Training
- ICML 2023NTK-approximating MLP Fusion for Efficient Language Model Fine-tuning
- ICML 2023On the convergence of the MLE as an estimator of the learning rate in the Exp3 algorithm
- ICML 2023Optimal Rates and Efficient Algorithms for Online Bayesian Persuasion
- ICML 2023Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks
- ICML 2023Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games
- ICML 2023PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search
- ICML 2023Probabilistic Categorical Adversarial Attack and Adversarial Training
- ICML 2023Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning
- ICML 2023Provable Data Subset Selection For Efficient Neural Networks Training
- ICML 2023Provably and Practically Efficient Neural Contextual Bandits
- ICML 2023Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs
- ICML 2023Revisiting Data-Free Knowledge Distillation with Poisoned Teachers
- ICML 2023Rockmate: an Efficient, Fast, Automatic and Generic Tool for Re-materialization in PyTorch
- ICML 2023Scaling Laws for Multilingual Neural Machine Translation
- ICML 2023Scaling Spherical CNNs
- ICML 2023Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory
- ICML 2023Semiparametrically Efficient Off-Policy Evaluation in Linear Markov Decision Processes
- ICML 2023Simple Hardware-Efficient Long Convolutions for Sequence Modeling
- ICML 2023Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability
- ICML 2023SLAMB: Accelerated Large Batch Training with Sparse Communication
- ICML 2023SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
- ICML 2023SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks at the Edge
- ICML 2023SpotEM: Efficient Video Search for Episodic Memory
- ICML 2023Stabilizing GANs' Training with Brownian Motion Controller
- ICML 2023SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient
- ICML 2023TAN Without a Burn: Scaling Laws of DP-SGD
- ICML 2023The case for 4-bit precision: k-bit Inference Scaling Laws
- ICML 2023Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks
- ICML 2023Towards Understanding and Improving GFlowNet Training
- ICML 2023Training Normalizing Flows from Dependent Data
- ICML 2023Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias
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。