高效训练论文趋势 2023–2026

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。

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 112 篇，第 1 / 3 页

1. NeurIPS 2023A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting
2. NeurIPS 2023A Hierarchical Training Paradigm for Antibody Structure-sequence Co-design
3. NeurIPS 2023A Smooth Binary Mechanism for Efficient Private Continual Observation
4. NeurIPS 2023Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation
5. NeurIPS 2023Actively Testing Your Model While It Learns: Realizing Label-Efficient Learning in Practice
6. NeurIPS 2023Adversarial Training from Mean Field Perspective
7. NeurIPS 2023Alternating Updates for Efficient Transformers
8. NeurIPS 2023Amortized Reparametrization: Efficient and Scalable Variational Inference for Latent SDEs
9. NeurIPS 2023An Efficient and Robust Framework for Approximate Nearest Neighbor Search with Attribute Constraint
10. NeurIPS 2023An Efficient End-to-End Training Approach for Zero-Shot Human-AI Coordination
11. NeurIPS 2023An Empirical Study Towards Prompt-Tuning for Graph Contrastive Pre-Training in Recommendations
12. NeurIPS 2023An Inverse Scaling Law for CLIP Training
13. NeurIPS 2023ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation
14. NeurIPS 2023Augmentation-Aware Self-Supervision for Data-Efficient GAN Training
15. NeurIPS 2023Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic Segmentation
16. NeurIPS 2023Bayes beats Cross Validation: Efficient and Accurate Ridge Regression via Expectation Maximization
17. NeurIPS 2023Birder: Communication-Efficient 1-bit Adaptive Optimizer for Practical Distributed DNN Training
18. NeurIPS 2023Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
19. NeurIPS 2023Clustering the Sketch: Dynamic Compression for Embedding Tables
20. NeurIPS 2023Composing Parameter-Efficient Modules with Arithmetic Operation
21. NeurIPS 2023Connecting Certified and Adversarial Training
22. NeurIPS 2023Coordinating Distributed Example Orders for Provably Accelerated Training
23. NeurIPS 2023CoPriv: Network/Protocol Co-Optimization for Communication-Efficient Private Inference
24. NeurIPS 2023Data Portraits: Recording Foundation Model Training Data
25. NeurIPS 2023Data Pruning via Moving-one-Sample-out
26. NeurIPS 2023Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training
27. NeurIPS 2023DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries
28. NeurIPS 2023Direct Training of SNN using Local Zeroth Order Method
29. NeurIPS 2023Distributionally Robust Ensemble of Lottery Tickets Towards Calibrated Sparse Network Training
30. NeurIPS 2023Does a sparse ReLU network training problem always admit an optimum ?
31. NeurIPS 2023Don’t just prune by magnitude! Your mask topology is a secret weapon
32. NeurIPS 2023DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
33. NeurIPS 2023Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers
34. NeurIPS 2023Efficient Activation Function Optimization through Surrogate Modeling
35. NeurIPS 2023Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection
36. NeurIPS 2023Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards
37. NeurIPS 2023Efficient Batched Algorithm for Contextual Linear Bandits with Large Action Space via Soft Elimination
38. NeurIPS 2023Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks
39. NeurIPS 2023Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks
40. NeurIPS 2023Efficient Learning of Linear Graph Neural Networks via Node Subsampling
41. NeurIPS 2023Efficient Online Clustering with Moving Costs
42. NeurIPS 2023Efficient Robust Bayesian Optimization for Arbitrary Uncertain inputs
43. NeurIPS 2023Efficient Subgame Refinement for Extensive-form Games
44. NeurIPS 2023Efficient Testable Learning of Halfspaces with Adversarial Label Noise
45. NeurIPS 2023Efficient Training of Energy-Based Models Using Jarzynski Equality
46. NeurIPS 2023EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding
47. NeurIPS 2023Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization
48. NeurIPS 2023Energy-Efficient Scheduling with Predictions
49. NeurIPS 2023Explainable and Efficient Randomized Voting Rules
50. NeurIPS 2023Exploring Loss Functions for Time-based Training Strategy in Spiking Neural Networks

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。