端上学习论文趋势 2023–2026

设备端训练

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 134 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

端上学习论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023900302122
202400224
202501012
202610326

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

全部端上学习论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 122 篇，第 2 / 3 页

  1. NeurIPS 2023Convergence Analysis of Sequential Federated Learning on Heterogeneous Data
  2. NeurIPS 2023Convolution Monge Mapping Normalization for learning on sleep data
  3. NeurIPS 2023Cookie Consent Has Disparate Impact on Estimation Accuracy
  4. NeurIPS 2023Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First
  5. NeurIPS 2023Doubly-Robust Self-Training
  6. NeurIPS 2023Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection
  7. NeurIPS 2023EMMA-X: An EM-like Multilingual Pre-training Algorithm for Cross-lingual Representation Learning
  8. NeurIPS 2023FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
  9. NeurIPS 2023Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration
  10. NeurIPS 2023HiBug: On Human-Interpretable Model Debug
  11. NeurIPS 2023Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality
  12. NeurIPS 2023Information Maximizing Curriculum: A Curriculum-Based Approach for Learning Versatile Skills
  13. NeurIPS 2023Large-Scale Distributed Learning via Private On-Device LSH
  14. NeurIPS 2023Latent SDEs on Homogeneous Spaces
  15. NeurIPS 2023Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation
  16. NeurIPS 2023Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions
  17. NeurIPS 2023Learning Provably Robust Estimators for Inverse Problems via Jittering
  18. NeurIPS 2023Learning to Augment Distributions for Out-of-distribution Detection
  19. NeurIPS 2023Learning Topology-Agnostic EEG Representations with Geometry-Aware Modeling
  20. NeurIPS 2023Learning via Wasserstein-Based High Probability Generalisation Bounds
  21. NeurIPS 2023Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training
  22. NeurIPS 2023May the Force be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations
  23. NeurIPS 2023Mitigating the Effect of Incidental Correlations on Part-based Learning
  24. NeurIPS 2023Mixed-Initiative Multiagent Apprenticeship Learning for Human Training of Robot Teams
  25. NeurIPS 2023On Convergence of Polynomial Approximations to the Gaussian Mixture Entropy
  26. NeurIPS 2023On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes
  27. NeurIPS 2023On Generalization Bounds for Projective Clustering
  28. NeurIPS 2023On Imitation in Mean-field Games
  29. NeurIPS 2023On kernel-based statistical learning theory in the mean field limit
  30. NeurIPS 2023On Robust Streaming for Learning with Experts: Algorithms and Lower Bounds
  31. NeurIPS 2023On Separate Normalization in Self-supervised Transformers
  32. NeurIPS 2023On Slicing Optimality for Mutual Information
  33. NeurIPS 2023On student-teacher deviations in distillation: does it pay to disobey?
  34. NeurIPS 2023On the Asymptotic Learning Curves of Kernel Ridge Regression under Power-law Decay
  35. NeurIPS 2023On the Convergence of Black-Box Variational Inference
  36. NeurIPS 2023On the Convergence of CART under Sufficient Impurity Decrease Condition
  37. NeurIPS 2023On the Convergence of Encoder-only Shallow Transformers
  38. NeurIPS 2023On the Convergence of No-Regret Learning Dynamics in Time-Varying Games
  39. NeurIPS 2023On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms
  40. NeurIPS 2023On the Exploitability of Instruction Tuning
  41. NeurIPS 2023On the Gini-impurity Preservation For Privacy Random Forests
  42. NeurIPS 2023On the Importance of Feature Separability in Predicting Out-Of-Distribution Error
  43. NeurIPS 2023On the Learnability of Multilabel Ranking
  44. NeurIPS 2023On the Minimax Regret for Online Learning with Feedback Graphs
  45. NeurIPS 2023On the Overlooked Structure of Stochastic Gradients
  46. NeurIPS 2023On the Pareto Front of Multilingual Neural Machine Translation
  47. NeurIPS 2023On the Robustness of Removal-Based Feature Attributions
  48. NeurIPS 2023On the Role of Entanglement and Statistics in Learning
  49. NeurIPS 2023On the Sublinear Regret of GP-UCB
  50. NeurIPS 2023On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training

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 查端上学习在 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": "on-device-learning"}

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端上学习论文？
共 134 篇，按年份分别是 2023 年 122 篇、2024 年 4 篇、2025 年 2 篇、2026 年 6 篇。
NeurIPS 2026 有多少篇端上学习论文？
NeurIPS 2026 有 1 篇端上学习论文。
ICLR 2025 有多少篇端上学习论文？
ICLR 2025 有 1 篇端上学习论文。
ICML 2026 有多少篇端上学习论文？
ICML 2026 有 3 篇端上学习论文。
CVPR 2026 有多少篇端上学习论文？
CVPR 2026 有 2 篇端上学习论文，上一届是 1 篇。
哪个会议的端上学习论文最多？
NeurIPS，2023–2026 年共 91 篇。

「边缘与物联网」下的其他主题