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 21 / 36 页

  1. NeurIPS 2025Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling
  2. NeurIPS 2025F-Adapter: Frequency-Adaptive Parameter-Efficient Fine-Tuning in Scientific Machine Learning
  3. NeurIPS 2025FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation
  4. NeurIPS 2025Fair Minimum Labeling: Efficient Temporal Network Activations for Reachability and Equity
  5. NeurIPS 2025FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing
  6. NeurIPS 2025FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language Models
  7. NeurIPS 2025First Attentions Last: Better Exploiting First Attentions for Efficient Parallel Training
  8. NeurIPS 2025FlashBias: Fast Computation of Attention with Bias
  9. NeurIPS 2025FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts
  10. NeurIPS 2025FraPPE: Fast and Efficient Preference-Based Pure Exploration
  11. NeurIPS 2025Frequency-Aware Token Reduction for Efficient Vision Transformer
  12. NeurIPS 2025Functional Scaling Laws in Kernel Regression: Loss Dynamics and Learning Rate Schedules
  13. NeurIPS 2025GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights
  14. NeurIPS 2025Gemstones: A Model Suite for Multi-Faceted Scaling Laws
  15. NeurIPS 2025Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update
  16. NeurIPS 2025Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts
  17. NeurIPS 2025GMV: A Unified and Efficient Graph Multi-View Learning Framework
  18. NeurIPS 2025Gradient Multi-Normalization for Efficient LLM Training
  19. NeurIPS 2025Group-Level Data Selection for Efficient Pretraining
  20. NeurIPS 2025GSPN-2: Efficient Parallel Sequence Modeling
  21. NeurIPS 2025Hadamard Test is Sufficient for Efficient Quantum Gradient Estimation with Lie Algebraic Symmetries
  22. NeurIPS 2025Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning
  23. NeurIPS 2025Hierachical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM
  24. NeurIPS 2025HiFC: High-efficiency Flash-based KV Cache Swapping for Scaling LLM Inference
  25. NeurIPS 2025HollowFlow: Efficient Sample Likelihood Evaluation using Hollow Message Passing
  26. NeurIPS 2025Hybrid Re-matching for Continual Learning with Parameter-Efficient Tuning
  27. NeurIPS 2025HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization
  28. NeurIPS 2025Hyperbolic Dataset Distillation
  29. NeurIPS 2025HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models
  30. NeurIPS 2025Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing
  31. NeurIPS 2025Improved Scaling Laws in Linear Regression via Data Reuse
  32. NeurIPS 2025Improving Decision Trees through the Lens of Parameterized Local Search
  33. NeurIPS 2025InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion
  34. NeurIPS 2025Interpretable and Parameter Efficient Graph Neural Additive Models with Random Fourier Features
  35. NeurIPS 2025Irrational Complex Rotations Empower Low-bit Optimizers
  36. NeurIPS 2025Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
  37. NeurIPS 2025Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization
  38. NeurIPS 2025Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation
  39. NeurIPS 2025Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning
  40. NeurIPS 2025LayerNavigator: Finding Promising Intervention Layers for Efficient Activation Steering in Large Language Models
  41. NeurIPS 2025Learned Prefix Caching for Efficient LLM Inference
  42. NeurIPS 2025Learning in Compact Spaces with Approximately Normalized Transformer
  43. NeurIPS 2025Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws
  44. NeurIPS 2025Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior
  45. NeurIPS 2025Linear Attention for Efficient Bidirectional Sequence Modeling
  46. NeurIPS 2025LLM at Network Edge: A Layer-wise Efficient Federated Fine-tuning Approach
  47. NeurIPS 2025LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision
  48. NeurIPS 2025LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades
  49. NeurIPS 2025Mamba Modulation: On the Length Generalization of Mamba Models
  50. NeurIPS 2025Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection

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