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 6 / 36 页
- ICLR 2026VQ-Transplant: Efficient VQ-Module Integration for Pre-trained Visual Tokenizers
- ICLR 2026What Scales in Cross-Entropy Scaling Law?
- ICLR 2026Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs
- ICLR 2026WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference
- ICLR 2026xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity
- ICLR 2026Your VAR Model is Secretly an Efficient and Explainable Generative Classifier
- ICLR 2026ZeroSiam: An Efficient Siamese for Test-Time Entropy Optimization without Collapse
- ICML 2026(1D) Ordered Tokens Enable Efficient Test-Time Search
- ICML 2026$\mu$pscaling small models: Principled warm starts and hyperparameter transfer
- ICML 2026A Bi-metric Framework for Efficient Nearest Neighbor Search
- ICML 2026A Geometry-Aware Efficient Algorithm for Compositional Entropic Risk Minimization
- ICML 2026A Provable Expressiveness Hierarchy in Hybrid Linear-Full Attention
- ICML 2026A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation
- ICML 2026Accelerating Langevin Monte Carlo via Efficient Stochastic Runge-Kutta Methods beyond Log-Concavity
- ICML 2026Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided Pruning
- ICML 2026Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance
- ICML 2026AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs
- ICML 2026An Information-Theoretic Criterion for Efficient Data Synthesis
- ICML 2026Artificial Hippocampus Networks for Efficient Long-Context Modeling
- ICML 2026ASTRA: Communication-Efficient Acceleration for Multi-Device Transformer Inference
- ICML 2026Attributed Network Alignment: Statistical Limits and Efficient Algorithm
- ICML 2026Beyond Pixels: Mining Compressed Domain Artifacts for Efficient AI-Generated Video Detection
- ICML 2026Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-Experts
- ICML 2026BiCrossNet with Decoupled Dual Generators: A Parameter‑Efficient and Generalizable Few‑Shot Custom Gesture Recognition Framework
- ICML 2026BioToken and BioFM – Biologically-Informed Tokenization Enables Accurate and Efficient Genomic Foundation Models
- ICML 2026Bounded Hyperbolic Tangent: A Stable and Efficient Alternative to Pre-Layer Normalization in Large Language Models
- ICML 2026Byte Pair Encoding for Efficient Time Series Forecasting
- ICML 2026Capacity-Aware Mixture Law Enables Efficient LLM Data Optimization
- ICML 2026CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs
- ICML 2026CauchyNet: Compact and Data-Efficient Learning using Holomorphic Activation Functions
- ICML 2026Compact Conformal Subgraphs
- ICML 2026Computationally-efficient Graph Modeling with Refined Graph Random Features
- ICML 2026Convolutional Learnable-Group Weightless Neural Network
- ICML 2026Curriculum-Guided Layer Scaling for Language Model Pretraining
- ICML 2026CurvZO: Adaptive Curvature-Guided Sparse Zeroth-Order Optimization for Efficient LLM Fine-Tuning
- ICML 2026DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers
- ICML 2026Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation
- ICML 2026Detecting the Semantic Fixed Point: A Geometric Framework for Efficient Inference
- ICML 2026Dissecting Quantization Error: A Concentration-Alignment Perspective
- ICML 2026Do Transformers Need Three Projections? Systematic Study of QKV Variants
- ICML 2026Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference
- ICML 2026Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos
- ICML 2026Dynamics of neural scaling laws in random feature regression with powerlaw-distributed kernel eigenvalues
- ICML 2026EchoAttention: Exploiting Token-Pair Redundancy and Frame-Block Similarity for Efficient Video Generation
- ICML 2026Effective Distillation to Hybrid xLSTM Architectures
- ICML 2026Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density
- ICML 2026Efficient Bayesian Inference from Noisy Pairwise Comparisons
- ICML 2026Efficient Bilevel Optimization for CKA-Guided MoE Upcycling
- ICML 2026Efficient Code Analysis via Graph Representation Learning-Guided Large Language Models
- ICML 2026Efficient Continuous-Depth Modeling with GRU Equivalents
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。