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 134 篇，第 1 / 3 页

  1. CVPR 2026DeDelayed Deleting Remote Inference Delay via On-Device Correction
  2. CVPR 2026Mobile-VTON High-Fidelity On-Device Virtual Try-On
  3. ICML 2026Efficient Preference Poisoning Attack on Offline RLHF
  4. ICML 2026Lower Bounds for Frank-Wolfe on Strongly Convex Sets
  5. ICML 2026On the Fragility of Data Attribution When Learning Is Distributed
  6. NeurIPS 2026MobileMoE: Scaling On-Device Mixture of Experts
  7. CVPR 2025EdgeTAM: On-Device Track Anything Model
  8. ICLR 2025Robust Function-Calling for On-Device Language Model via Function Masking
  9. CVPR 2024Cloud-Device Collaborative Learning for Multimodal Large Language Models
  10. CVPR 2024Device-Wise Federated Network Pruning
  11. ICML 2024MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
  12. ICML 2024On Online Experimentation without Device Identifiers
  13. CVPR 2023Efficient On-Device Training via Gradient Filtering
  14. CVPR 2023TMO: Textured Mesh Acquisition of Objects With a Mobile Device by Using Differentiable Rendering
  15. ICML 2023A Mathematical Model for Curriculum Learning for Parities
  16. ICML 2023Adaptive Smoothing Gradient Learning for Spiking Neural Networks
  17. ICML 2023Adversarial Collaborative Learning on Non-IID Features
  18. ICML 2023An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning
  19. ICML 2023Block Subsampled Randomized Hadamard Transform for Nyström Approximation on Distributed Architectures
  20. ICML 2023Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting
  21. ICML 2023Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network
  22. ICML 2023Correcting discount-factor mismatch in on-policy policy gradient methods
  23. ICML 2023Cramming: Training a Language Model on a single GPU in one day.
  24. ICML 2023Differentially Private Optimization on Large Model at Small Cost
  25. ICML 2023Feature Directions Matter: Long-Tailed Learning via Rotated Balanced Representation
  26. ICML 2023FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization
  27. ICML 2023Global Selection of Contrastive Batches via Optimization on Sample Permutations
  28. ICML 2023Learning Globally Smooth Functions on Manifolds
  29. ICML 2023Learning Preconditioners for Conjugate Gradient PDE Solvers
  30. ICML 2023Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial Optimization
  31. ICML 2023On Many-Actions Policy Gradient
  32. ICML 2023On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization
  33. ICML 2023On the Privacy-Robustness-Utility Trilemma in Distributed Learning
  34. ICML 2023On Uni-Modal Feature Learning in Supervised Multi-Modal Learning
  35. ICML 2023PixelAsParam: A Gradient View on Diffusion Sampling with Guidance
  36. ICML 2023Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons
  37. ICML 2023Provably Invariant Learning without Domain Information
  38. ICML 2023Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL
  39. ICML 2023QASA: Advanced Question Answering on Scientific Articles
  40. ICML 2023Rethinking Weak Supervision in Helping Contrastive Learning
  41. ICML 2023StriderNet: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes
  42. ICML 2023Theoretical Bounds on the Network Community Profile from Low-rank Semi-definite Programming
  43. ICML 2023Towards Robust Graph Incremental Learning on Evolving Graphs
  44. ICML 2023Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression
  45. NeurIPS 2023[Re] Numerical influence of ReLU'(0) on backpropagation
  46. NeurIPS 2023[Re] On the Reproducibility of CartoonX
  47. NeurIPS 2023A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction
  48. NeurIPS 2023A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning
  49. NeurIPS 2023A Unified Algorithm Framework for Unsupervised Discovery of Skills based on Determinantal Point Process
  50. NeurIPS 2023A Variational Perspective on High-Resolution ODEs

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