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 419 篇，第 6 / 9 页
- ICLR 2025Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
- ICLR 2025Scaling Laws for Adversarial Attacks on Language Model Activations and Tokens
- ICLR 2025Scaling Laws for Precision
- ICLR 2025Scaling Optimal LR Across Token Horizons
- ICLR 2025Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study
- ICLR 2025SelectFormer in Data Markets: Privacy-Preserving and Efficient Data Selection for Transformers with Multi-Party Computation
- ICLR 2025Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts
- ICLR 2025Skill Expansion and Composition in Parameter Space
- ICLR 2025SONICS: Synthetic Or Not - Identifying Counterfeit Songs
- ICLR 2025SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking
- ICLR 2025Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
- ICLR 2025Structural-Entropy-Based Sample Selection for Efficient and Effective Learning
- ICLR 2025Surprising Effectiveness of pretraining Ternary Language Model at Scale
- ICLR 2025The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws
- ICLR 2025ThunderKittens: Simple, Fast, and $\textit{Adorable}$ Kernels
- ICLR 2025TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation
- ICLR 2025TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
- ICLR 2025Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning
- ICLR 2025Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models
- ICLR 2025u-$\mu$P: The Unit-Scaled Maximal Update Parametrization
- ICLR 2025U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models
- ICLR 2025Unified Parameter-Efficient Unlearning for LLMs
- ICLR 2025Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning
- ICLR 2025ZETA: Leveraging $Z$-order Curves for Efficient Top-$k$ Attention
- ICLR 2024Adaptive Window Pruning for Efficient Local Motion Deblurring
- ICLR 2024ALAM: Averaged Low-Precision Activation for Memory-Efficient Training of Transformer Models
- ICLR 2024ASMR: Activation-Sharing Multi-Resolution Coordinate Networks for Efficient Inference
- ICLR 2024AutoChunk: Automated Activation Chunk for Memory-Efficient Deep Learning Inference
- ICLR 2024AutoVP: An Automated Visual Prompting Framework and Benchmark
- ICLR 2024BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation
- ICLR 2024CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding
- ICLR 2024Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces
- ICLR 2024Dictionary Contrastive Learning for Efficient Local Supervision without Auxiliary Networks
- ICLR 2024Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks
- ICLR 2024DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
- ICLR 2024Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation
- ICLR 2024Dynamic Sparse Training with Structured Sparsity
- ICLR 2024Effective and Efficient Federated Tree Learning on Hybrid Data
- ICLR 2024Efficient Backpropagation with Variance Controlled Adaptive Sampling
- ICLR 2024Efficient ConvBN Blocks for Transfer Learning and Beyond
- ICLR 2024Efficient Heterogeneous Meta-Learning via Channel Shuffling Modulation
- ICLR 2024Efficient local linearity regularization to overcome catastrophic overfitting
- ICLR 2024Efficient Modulation for Vision Networks
- ICLR 2024Efficient Score Matching with Deep Equilibrium Layers
- ICLR 2024Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models
- ICLR 2024Efficient Streaming Language Models with Attention Sinks
- ICLR 2024Efficient Subgraph GNNs by Learning Effective Selection Policies
- ICLR 2024Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Products
- ICLR 2024Fair and Efficient Contribution Valuation for Vertical Federated Learning
- ICLR 2024Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models
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。