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

每年论文数

各会议论文数

按年份和会议统计

高效训练论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023112678384346
2024207812280300
202519012611882516
2026177148169109603

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

全部高效训练论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 499 篇，第 10 / 10 页

  1. NeurIPS 2023MGDD: A Meta Generator for Fast Dataset Distillation
  2. NeurIPS 2023MixFormerV2: Efficient Fully Transformer Tracking
  3. NeurIPS 2023MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining
  4. NeurIPS 2023Multiplication-Free Transformer Training via Piecewise Affine Operations
  5. NeurIPS 2023NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks
  6. NeurIPS 2023Neural Priming for Sample-Efficient Adaptation
  7. NeurIPS 2023NICE: NoIse-modulated Consistency rEgularization for Data-Efficient GANs
  8. NeurIPS 2023No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models
  9. NeurIPS 2023On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
  10. NeurIPS 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models
  11. NeurIPS 2023Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
  12. NeurIPS 2023PDP: Parameter-free Differentiable Pruning is All You Need
  13. NeurIPS 2023Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources
  14. NeurIPS 2023Pre-RMSNorm and Pre-CRMSNorm Transformers: Equivalent and Efficient Pre-LN Transformers
  15. NeurIPS 2023Progressive Ensemble Distillation: Building Ensembles for Efficient Inference
  16. NeurIPS 2023QLoRA: Efficient Finetuning of Quantized LLMs
  17. NeurIPS 2023RangePerception: Taming LiDAR Range View for Efficient and Accurate 3D Object Detection
  18. NeurIPS 2023ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
  19. NeurIPS 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting
  20. NeurIPS 2023RETVec: Resilient and Efficient Text Vectorizer
  21. NeurIPS 2023Reusing Pretrained Models by Multi-linear Operators for Efficient Training
  22. NeurIPS 2023Sample-efficient Multi-objective Molecular Optimization with GFlowNets
  23. NeurIPS 2023ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection
  24. NeurIPS 2023Scaling Data-Constrained Language Models
  25. NeurIPS 2023ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer
  26. NeurIPS 2023SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling
  27. NeurIPS 2023SLaM: Student-Label Mixing for Distillation with Unlabeled Examples
  28. NeurIPS 2023Slimmed Asymmetrical Contrastive Learning and Cross Distillation for Lightweight Model Training
  29. NeurIPS 2023Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks
  30. NeurIPS 2023Sparse Modular Activation for Efficient Sequence Modeling
  31. NeurIPS 2023SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networks
  32. NeurIPS 2023Sparsity-Preserving Differentially Private Training of Large Embedding Models
  33. NeurIPS 2023Speculative Decoding with Big Little Decoder
  34. NeurIPS 2023Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective
  35. NeurIPS 2023Stable Nonconvex-Nonconcave Training via Linear Interpolation
  36. NeurIPS 2023Text Alignment Is An Efficient Unified Model for Massive NLP Tasks
  37. NeurIPS 2023To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis
  38. NeurIPS 2023Towards Accelerated Model Training via Bayesian Data Selection
  39. NeurIPS 2023Towards Efficient and Accurate Winograd Convolution via Full Quantization
  40. NeurIPS 2023Towards Efficient Pre-Trained Language Model via Feature Correlation Distillation
  41. NeurIPS 2023Train 'n Trade: Foundations of Parameter Markets
  42. NeurIPS 2023Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models
  43. NeurIPS 2023Training Transformers with 4-bit Integers
  44. NeurIPS 2023TRIAGE: Characterizing and auditing training data for improved regression
  45. NeurIPS 2023Triangulation Residual Loss for Data-efficient 3D Pose Estimation
  46. NeurIPS 2023VCC: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens
  47. NeurIPS 2023VPGTrans: Transfer Visual Prompt Generator across LLMs
  48. NeurIPS 2023xTrimoGene: An Efficient and Scalable Representation Learner for Single-Cell RNA-Seq Data
  49. NeurIPS 2023ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking

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"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「效率与系统」下的其他主题