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 23 / 36 页
- NeurIPS 2025Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models
- NeurIPS 2025Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism
- NeurIPS 2025SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training
- NeurIPS 2025SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training
- NeurIPS 2025Superposition Yields Robust Neural Scaling
- NeurIPS 2025SymMaP: Improving Computational Efficiency in Linear Solvers through Symbolic Preconditioning
- NeurIPS 2025Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers
- NeurIPS 2025Teaching Transformers to Solve Combinatorial Problems through Efficient Trial & Error
- NeurIPS 2025Technical Debt in In-Context Learning: Diminishing Efficiency in Long Context
- NeurIPS 2025The Omni-Expert: A Computationally Efficient Approach to Achieve a Mixture of Experts in a Single Expert Model
- NeurIPS 2025Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
- NeurIPS 2025Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few
- NeurIPS 2025TrajMamba: An Efficient and Semantic-rich Vehicle Trajectory Pre-training Model
- NeurIPS 2025UMoE: Unifying Attention and FFN with Shared Experts
- NeurIPS 2025Unified Scaling Laws for Compressed Representations
- NeurIPS 2025V2V: Scaling Event-Based Vision through Efficient Video-to-Voxel Simulation
- NeurIPS 2025Venus-MAXWELL: Efficient Learning of Protein-Mutation Stability Landscapes using Protein Language Models
- NeurIPS 2025Zebra-Llama: Towards Extremely Efficient Hybrid Models
- NeurIPS 2025ZeroS: Zero‑Sum Linear Attention for Efficient Transformers
- CVPR 20243DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos
- CVPR 2024A General and Efficient Training for Transformer via Token Expansion
- CVPR 2024A Simple Baseline for Efficient Hand Mesh Reconstruction
- CVPR 2024Adversarial Score Distillation: When score distillation meets GAN
- CVPR 2024ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers
- CVPR 2024An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning
- CVPR 2024Are Conventional SNNs Really Efficient? A Perspective from Network Quantization
- CVPR 2024Boosting Image Quality Assessment through Efficient Transformer Adaptation with Local Feature Enhancement
- CVPR 2024CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization
- CVPR 2024Characteristics Matching Based Hash Codes Generation for Efficient Fine-grained Image Retrieval
- CVPR 2024Circuit Design and Efficient Simulation of Quantum Inner Product and Empirical Studies of Its Effect on Near-Term Hybrid Quantum-Classic Machine Learning
- CVPR 2024CLIP-KD: An Empirical Study of CLIP Model Distillation
- CVPR 2024Communication-Efficient Collaborative Perception via Information Filling with Codebook
- CVPR 2024Communication-Efficient Federated Learning with Accelerated Client Gradient
- CVPR 2024Data-Efficient Multimodal Fusion on a Single GPU
- CVPR 2024Data-Efficient Unsupervised Interpolation Without Any Intermediate Frame for 4D Medical Images
- CVPR 2024Deep-TROJ: An Inference Stage Trojan Insertion Algorithm through Efficient Weight Replacement Attack
- CVPR 2024Distilling Semantic Priors from SAM to Efficient Image Restoration Models
- CVPR 2024ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning
- CVPR 2024Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapes
- CVPR 2024Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment
- CVPR 2024Efficient Hyperparameter Optimization with Adaptive Fidelity Identification
- CVPR 2024Efficient Meshflow and Optical Flow Estimation from Event Cameras
- CVPR 2024Efficient Model Stealing Defense with Noise Transition Matrix
- CVPR 2024Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring
- CVPR 2024Efficient Multitask Dense Predictor via Binarization
- CVPR 2024Efficient Privacy-Preserving Visual Localization Using 3D Ray Clouds
- CVPR 2024Efficient Scene Recovery Using Luminous Flux Prior
- CVPR 2024Efficient Solution of Point-Line Absolute Pose
- CVPR 2024Efficient Stitchable Task Adaptation
- CVPR 2024EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation
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。