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 499 篇，第 5 / 10 页
- NeurIPS 2025CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs
- NeurIPS 2025CoIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization
- NeurIPS 2025Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo
- NeurIPS 2025Computation and Memory-Efficient Model Compression with Gradient Reweighting
- NeurIPS 2025Computational Budget Should Be Considered in Data Selection
- NeurIPS 2025Convex Potential Mirror Langevin Algorithm for Efficient Sampling of Energy-Based Models
- NeurIPS 2025Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning
- NeurIPS 2025CrossSpectra: Exploiting Cross-Layer Smoothness for Parameter-Efficient Fine-Tuning
- NeurIPS 2025D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstruction
- NeurIPS 2025DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization
- NeurIPS 2025Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency
- NeurIPS 2025Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction
- NeurIPS 2025DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method
- NeurIPS 2025Dependency Parsing is More Parameter-Efficient with Normalization
- NeurIPS 2025DictPFL: Efficient and Private Federated Learning on Encrypted Gradients
- NeurIPS 2025Diffusion on Demand: Selective Caching and Modulation for Efficient Generation
- NeurIPS 2025Dimension-adapted Momentum Outscales SGD
- NeurIPS 2025DoDo-Code: an Efficient Levenshtein Distance Embedding-based Code for 4-ary IDS Channel
- NeurIPS 2025Don't be lazy: CompleteP enables compute-efficient deep transformers
- NeurIPS 2025DuSA: Fast and Accurate Dual-Stage Sparse Attention Mechanism Accelerating Both Training and Inference
- NeurIPS 2025DynaNav: Dynamic Feature and Layer Selection for Efficient Visual Navigation
- NeurIPS 2025E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products
- NeurIPS 2025EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU Utilization
- NeurIPS 2025ECO: Evolving Core Knowledge for Efficient Transfer
- NeurIPS 2025Efficient $k$-Sparse Band–Limited Interpolation with Improved Approximation Ratio
- NeurIPS 2025Efficient and Generalizable Mixed-Precision Quantization via Topological Entropy
- NeurIPS 2025Efficient Data Selection at Scale via Influence Distillation
- NeurIPS 2025Efficient Fairness-Performance Pareto Front Computation
- NeurIPS 2025Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning
- NeurIPS 2025Efficient Kernelized Learning in Polyhedral Games beyond Full Information: From Colonel Blotto to Congestion Games
- NeurIPS 2025Efficient Large Language Model Inference with Neural Block Linearization
- NeurIPS 2025Efficient Last-Iterate Convergence in Solving Extensive-Form Games
- NeurIPS 2025Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling
- NeurIPS 2025Efficient Multi-modal Large Language Models via Progressive Consistency Distillation
- NeurIPS 2025Efficient Multimodal Dataset Distillation via Generative Models
- NeurIPS 2025Efficient PAC Learning for Realizable-Statistic Models via Convex Surrogates
- NeurIPS 2025Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems
- NeurIPS 2025Efficient Part-level 3D Object Generation via Dual Volume Packing
- NeurIPS 2025Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference
- NeurIPS 2025Efficient RAW Image Deblurring with Adaptive Frequency Modulation
- NeurIPS 2025Efficient Representativeness-Aware Coreset Selection
- NeurIPS 2025Efficient semantic uncertainty quantification in language models via diversity-steered sampling
- NeurIPS 2025Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space
- NeurIPS 2025Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery
- NeurIPS 2025Efficient Verified Unlearning For Distillation
- NeurIPS 2025ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets
- NeurIPS 2025Emergence and scaling laws in SGD learning of shallow neural networks
- NeurIPS 2025EventMG: Efficient Multilevel Mamba-Graph Learning for Spatiotemporal Event Representation
- NeurIPS 2025Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling
- NeurIPS 2025F-Adapter: Frequency-Adaptive Parameter-Efficient Fine-Tuning in Scientific Machine Learning
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。