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 355 篇，第 4 / 8 页

  1. CVPR 2025Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning
  2. CVPR 2025GroupMamba: Efficient Group-Based Visual State Space Model
  3. CVPR 2025Improving the Training of Data-Efficient GANs via Quality Aware Dynamic Discriminator Rejection Sampling
  4. CVPR 2025K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences
  5. CVPR 2025Keep the Balance: A Parameter-Efficient Symmetrical Framework for RGB+X Semantic Segmentation
  6. CVPR 2025Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
  7. CVPR 2025Less is More: Efficient Image Vectorization with Adaptive Parameterization
  8. CVPR 2025Less is More: Efficient Model Merging with Binary Task Switch
  9. CVPR 2025Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition
  10. CVPR 2025LoKi: Low-dimensional KAN for Efficient Fine-tuning Image Models
  11. CVPR 2025MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Action Anticipation
  12. CVPR 2025MEET: Towards Memory-Efficient Temporal Sparse Deep Neural Networks
  13. CVPR 2025Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning
  14. CVPR 2025MoST: Efficient Monarch Sparse Tuning for 3D Representation Learning
  15. CVPR 2025No Pains, More Gains: Recycling Sub-Salient Patches for Efficient High-Resolution Image Recognition
  16. CVPR 2025NoT: Federated Unlearning via Weight Negation
  17. CVPR 2025NVILA: Efficient Frontier Visual Language Models
  18. CVPR 2025Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation
  19. CVPR 2025Practical Solutions to the Relative Pose of Three Calibrated Cameras
  20. CVPR 2025Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness
  21. CVPR 2025Proximal Algorithm Unrolling: Flexible and Efficient Reconstruction Networks for Single-Pixel Imaging
  22. CVPR 2025PS-EIP: Robust Photometric Stereo Based on Event Interval Profile
  23. CVPR 2025Query Efficient Black-Box Visual Prompting with Subspace Learning
  24. CVPR 2025Rethinking Token Reduction with Parameter-Efficient Fine-Tuning in ViT for Pixel-Level Tasks
  25. CVPR 2025RivuletMLP: An MLP-based Architecture for Efficient Compressed Video Quality Enhancement
  26. CVPR 2025Sample- and Parameter-Efficient Auto-Regressive Image Models
  27. CVPR 2025Scale Efficient Training for Large Datasets
  28. CVPR 2025Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentation
  29. CVPR 2025SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation
  30. CVPR 2025Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch
  31. CVPR 2025SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer
  32. CVPR 2025Spatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecasting
  33. CVPR 2025Style Quantization for Data-Efficient GAN Training
  34. CVPR 2025TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion
  35. CVPR 2025TADFormer: Task-Adaptive Dynamic TransFormer for Efficient Multi-Task Learning
  36. CVPR 2025Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding
  37. CVPR 2025Towards Efficient Foundation Model for Zero-shot Amodal Segmentation
  38. CVPR 2025Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory
  39. CVPR 2025Trajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSM
  40. CVPR 2025Two is Better than One: Efficient Ensemble Defense for Robust and Compact Models
  41. CVPR 2025ViKIENet: Towards Efficient 3D Object Detection with Virtual Key Instance Enhanced Network
  42. CVPR 20243DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos
  43. CVPR 2024A General and Efficient Training for Transformer via Token Expansion
  44. CVPR 2024A Simple Baseline for Efficient Hand Mesh Reconstruction
  45. CVPR 2024Adversarial Score Distillation: When score distillation meets GAN
  46. CVPR 2024ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers
  47. CVPR 2024An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning
  48. CVPR 2024Are Conventional SNNs Really Efficient? A Perspective from Network Quantization
  49. CVPR 2024Boosting Image Quality Assessment through Efficient Transformer Adaptation with Local Feature Enhancement
  50. CVPR 2024CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization

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