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 29 / 36 页
- NeurIPS 2024A Label is Worth A Thousand Images in Dataset Distillation
- NeurIPS 2024AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment
- NeurIPS 2024BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
- NeurIPS 2024DeltaDock: A Unified Framework for Accurate, Efficient, and Physically Reliable Molecular Docking
- NeurIPS 2024E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation
- NeurIPS 2024Efficient Convex Algorithms for Universal Kernel Learning
- NeurIPS 2024FedGMKD: An Efficient Prototype Federated Learning Framework through Knowledge Distillation and Discrepancy-Aware Aggregation
- NeurIPS 2024Genetic-guided GFlowNets for Sample Efficient Molecular Optimization
- NeurIPS 2024LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment
- NeurIPS 2024LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing
- NeurIPS 2024Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
- NeurIPS 2024Provable and Efficient Dataset Distillation for Kernel Ridge Regression
- NeurIPS 2024Rough Transformers: Lightweight and Continuous Time Series Modelling through Signature Patching
- NeurIPS 2024Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies
- NeurIPS 2024Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices
- NeurIPS 2024SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining
- NeurIPS 2024SpaFL: Communication-Efficient Federated Learning With Sparse Models And Low Computational Overhead
- NeurIPS 2024TorchOpt: An Efficient Library for Differentiable Optimization
- NeurIPS 2024V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark
- CVPR 2023A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization
- CVPR 2023Accelerating Dataset Distillation via Model Augmentation
- CVPR 2023Adapting Shortcut With Normalizing Flow: An Efficient Tuning Framework for Visual Recognition
- CVPR 2023AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation
- CVPR 2023Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-Time Mobile Telepresence
- CVPR 2023BEV-LaneDet: An Efficient 3D Lane Detection Based on Virtual Camera via Key-Points
- CVPR 2023Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers
- CVPR 2023C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation
- CVPR 2023Complexity-Guided Slimmable Decoder for Efficient Deep Video Compression
- CVPR 2023Comprehensive and Delicate: An Efficient Transformer for Image Restoration
- CVPR 2023Constructing Deep Spiking Neural Networks From Artificial Neural Networks With Knowledge Distillation
- CVPR 2023Content-Aware Token Sharing for Efficient Semantic Segmentation With Vision Transformers
- CVPR 2023Context-Aware Pretraining for Efficient Blind Image Decomposition
- CVPR 2023CUF: Continuous Upsampling Filters
- CVPR 2023Data-Efficient Large Scale Place Recognition With Graded Similarity Supervision
- CVPR 2023Decentralized Learning With Multi-Headed Distillation
- CVPR 2023Deep Discriminative Spatial and Temporal Network for Efficient Video Deblurring
- CVPR 2023Differentiable Shadow Mapping for Efficient Inverse Graphics
- CVPR 2023DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training
- CVPR 2023DistilPose: Tokenized Pose Regression With Heatmap Distillation
- CVPR 2023Don't Lie to Me! Robust and Efficient Explainability With Verified Perturbation Analysis
- CVPR 2023Efficient and Explicit Modelling of Image Hierarchies for Image Restoration
- CVPR 2023Efficient Frequency Domain-Based Transformers for High-Quality Image Deblurring
- CVPR 2023Efficient Loss Function by Minimizing the Detrimental Effect of Floating-Point Errors on Gradient-Based Attacks
- CVPR 2023Efficient Map Sparsification Based on 2D and 3D Discretized Grids
- CVPR 2023Efficient Mask Correction for Click-Based Interactive Image Segmentation
- CVPR 2023Efficient Movie Scene Detection Using State-Space Transformers
- CVPR 2023Efficient Multimodal Fusion via Interactive Prompting
- CVPR 2023Efficient On-Device Training via Gradient Filtering
- CVPR 2023Efficient RGB-T Tracking via Cross-Modality Distillation
- CVPR 2023Efficient Robust Principal Component Analysis via Block Krylov Iteration and CUR Decomposition
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。