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 1,765 篇，第 24 / 36 页

  1. CVPR 2024ERMVP: Communication-Efficient and Collaboration-Robust Multi-Vehicle Perception in Challenging Environments
  2. CVPR 2024Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation
  3. CVPR 2024Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios
  4. CVPR 2024FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action Segmentation
  5. CVPR 2024FedMef: Towards Memory-efficient Federated Dynamic Pruning
  6. CVPR 2024FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding
  7. CVPR 2024FlowIE: Efficient Image Enhancement via Rectified Flow
  8. CVPR 2024Gradient-based Parameter Selection for Efficient Fine-Tuning
  9. CVPR 2024Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation
  10. CVPR 2024How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?
  11. CVPR 2024HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces
  12. CVPR 2024Integrating Efficient Optimal Transport and Functional Maps For Unsupervised Shape Correspondence Learning
  13. CVPR 2024Kandinsky Conformal Prediction: Efficient Calibration of Image Segmentation Algorithms
  14. CVPR 2024Label-Efficient Group Robustness via Out-of-Distribution Concept Curation
  15. CVPR 2024LEOD: Label-Efficient Object Detection for Event Cameras
  16. CVPR 2024Leveraging Camera Triplets for Efficient and Accurate Structure-from-Motion
  17. CVPR 2024Logit Standardization in Knowledge Distillation
  18. CVPR 2024Look-Up Table Compression for Efficient Image Restoration
  19. CVPR 2024LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels
  20. CVPR 2024MCNet: Rethinking the Core Ingredients for Accurate and Efficient Homography Estimation
  21. CVPR 2024MS-DETR: Efficient DETR Training with Mixed Supervision
  22. CVPR 2024NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation
  23. CVPR 2024On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm
  24. CVPR 2024Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model
  25. CVPR 2024PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution
  26. CVPR 2024PEM: Prototype-based Efficient MaskFormer for Image Segmentation
  27. CVPR 2024PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees
  28. CVPR 2024PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild
  29. CVPR 2024Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network
  30. CVPR 2024Querying as Prompt: Parameter-Efficient Learning for Multimodal Language Model
  31. CVPR 2024Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization
  32. CVPR 2024Resource-Efficient Transformer Pruning for Finetuning of Large Models
  33. CVPR 2024Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples
  34. CVPR 2024S2MVTC: a Simple yet Efficient Scalable Multi-View Tensor Clustering
  35. CVPR 2024Scalable 3D Registration via Truncated Entry-wise Absolute Residuals
  36. CVPR 2024Scaled Decoupled Distillation
  37. CVPR 2024Scaling Laws of Synthetic Images for Model Training ... for Now
  38. CVPR 2024SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation
  39. CVPR 2024Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors
  40. CVPR 2024SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design
  41. CVPR 2024SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction
  42. CVPR 2024Structured Model Probing: Empowering Efficient Transfer Learning by Structured Regularization
  43. CVPR 2024SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective
  44. CVPR 2024Teeth-SEG: An Efficient Instance Segmentation Framework for Orthodontic Treatment based on Multi-Scale Aggregation and Anthropic Prior Knowledge
  45. CVPR 2024Time- Memory- and Parameter-Efficient Visual Adaptation
  46. CVPR 2024Time-Efficient Light-Field Acquisition Using Coded Aperture and Events
  47. CVPR 2024Towards Efficient Replay in Federated Incremental Learning
  48. CVPR 2024UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory
  49. CVPR 2024VkD: Improving Knowledge Distillation using Orthogonal Projections
  50. ICLR 2024Adaptive Window Pruning for Efficient Local Motion Deblurring

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