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 27 / 36 页

  1. ICML 2024Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts
  2. ICML 2024Differentiable Model Scaling using Differentiable Topk
  3. ICML 2024DiJiang: Efficient Large Language Models through Compact Kernelization
  4. ICML 2024Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control
  5. ICML 2024DistiLLM: Towards Streamlined Distillation for Large Language Models
  6. ICML 2024Distributed High-Dimensional Quantile Regression: Estimation Efficiency and Support Recovery
  7. ICML 2024Do Topological Characteristics Help in Knowledge Distillation?
  8. ICML 2024Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond
  9. ICML 2024Efficient Algorithms for Sum-Of-Minimum Optimization
  10. ICML 2024Efficient and Effective Time-Series Forecasting with Spiking Neural Networks
  11. ICML 2024Efficient Contextual Bandits with Uninformed Feedback Graphs
  12. ICML 2024Efficient Contrastive Learning for Fast and Accurate Inference on Graphs
  13. ICML 2024Efficient Exploration for LLMs
  14. ICML 2024Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits
  15. ICML 2024Efficient Mixture Learning in Black-Box Variational Inference
  16. ICML 2024Efficient Online Set-valued Classification with Bandit Feedback
  17. ICML 2024Efficient PAC Learnability of Dynamical Systems Over Multilayer Networks
  18. ICML 2024Efficient Precision and Recall Metrics for Assessing Generative Models using Hubness-aware Sampling
  19. ICML 2024Efficient Stochastic Approximation of Minimax Excess Risk Optimization
  20. ICML 2024Efficient Value Iteration for s-rectangular Robust Markov Decision Processes
  21. ICML 2024Embodied CoT Distillation From LLM To Off-the-shelf Agents
  22. ICML 2024EMC$^2$: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence
  23. ICML 2024Energy-Efficient Gaussian Processes Using Low-Precision Arithmetic
  24. ICML 2024Error Feedback Can Accurately Compress Preconditioners
  25. ICML 2024ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections
  26. ICML 2024EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens
  27. ICML 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model
  28. ICML 2024Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits
  29. ICML 2024Fast Decision Boundary based Out-of-Distribution Detector
  30. ICML 2024Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training
  31. ICML 2024FedBAT: Communication-Efficient Federated Learning via Learnable Binarization
  32. ICML 2024FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models
  33. ICML 2024Flextron: Many-in-One Flexible Large Language Model
  34. ICML 2024Gated Linear Attention Transformers with Hardware-Efficient Training
  35. ICML 2024GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
  36. ICML 2024Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference
  37. ICML 2024Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization
  38. ICML 2024Graph Distillation with Eigenbasis Matching
  39. ICML 2024GroupCover: A Secure, Efficient and Scalable Inference Framework for On-device Model Protection based on TEEs
  40. ICML 2024InferCept: Efficient Intercept Support for Augmented Large Language Model Inference
  41. ICML 2024InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models
  42. ICML 2024Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization
  43. ICML 2024Knowledge Distillation with Auxiliary Variable
  44. ICML 2024Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs
  45. ICML 2024Learning-Efficient Yet Generalizable Collaborative Filtering for Item Recommendation
  46. ICML 2024Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference
  47. ICML 2024Measuring Stochastic Data Complexity with Boltzmann Influence Functions
  48. ICML 2024Memory Efficient Neural Processes via Constant Memory Attention Block
  49. ICML 2024MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data Utilization
  50. ICML 2024Multi-Region Markovian Gaussian Process: An Efficient Method to Discover Directional Communications Across Multiple Brain Regions

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