端上学习论文趋势 2023–2026

主要结论

• 端上学习论文从 2023 年的 122 篇降到 2026 年的 6 篇，热度在回落。
• NeurIPS 是发端上学习论文最多的会议，2023–2026 年共 91 篇，占四个会议总量的 68%。
• 在「边缘与物联网」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的传感融合是 3.8 倍，端上学习是 0.0 倍。

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

• NeurIPS 2026MobileMoE: Scaling On-Device Mixture of Experts
• ICML 2026Lower Bounds for Frank-Wolfe on Strongly Convex Sets
• CVPR 2026DeDelayed Deleting Remote Inference Delay via On-Device Correction
• ICLR 2025Robust Function-Calling for On-Device Language Model via Function Masking
• CVPR 2025EdgeTAM: On-Device Track Anything Model
• ICML 2024MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
• CVPR 2024Device-Wise Federated Network Pruning
• NeurIPS 2023[Re] Numerical influence of ReLU'(0) on backpropagation
• ICML 2023Adversarial Collaborative Learning on Non-IID Features
• CVPR 2023Efficient On-Device Training via Gradient Filtering
• ICML 2026On the Fragility of Data Attribution When Learning Is Distributed
• CVPR 2026Mobile-VTON High-Fidelity On-Device Virtual Try-On
• ICML 2024On Online Experimentation without Device Identifiers
• CVPR 2024Cloud-Device Collaborative Learning for Multimodal Large Language Models
• NeurIPS 2023[Re] On the Reproducibility of CartoonX
• ICML 2023FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization
• CVPR 2023TMO: Textured Mesh Acquisition of Objects With a Mobile Device by Using Differentiable Rendering
• ICML 2026Efficient Preference Poisoning Attack on Offline RLHF
• NeurIPS 2023A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning
• ICML 2023Towards Robust Graph Incremental Learning on Evolving Graphs

全部端上学习论文

共 35 篇，第 1 / 1 页

1. ICML 2026Efficient Preference Poisoning Attack on Offline RLHF
2. ICML 2026Lower Bounds for Frank-Wolfe on Strongly Convex Sets
3. ICML 2026On the Fragility of Data Attribution When Learning Is Distributed
4. ICML 2024MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
5. ICML 2024On Online Experimentation without Device Identifiers
6. ICML 2023A Mathematical Model for Curriculum Learning for Parities
7. ICML 2023Adaptive Smoothing Gradient Learning for Spiking Neural Networks
8. ICML 2023Adversarial Collaborative Learning on Non-IID Features
9. ICML 2023An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning
10. ICML 2023Block Subsampled Randomized Hadamard Transform for Nyström Approximation on Distributed Architectures
11. ICML 2023Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting
12. ICML 2023Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network
13. ICML 2023Correcting discount-factor mismatch in on-policy policy gradient methods
14. ICML 2023Cramming: Training a Language Model on a single GPU in one day.
15. ICML 2023Differentially Private Optimization on Large Model at Small Cost
16. ICML 2023Feature Directions Matter: Long-Tailed Learning via Rotated Balanced Representation
17. ICML 2023FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization
18. ICML 2023Global Selection of Contrastive Batches via Optimization on Sample Permutations
19. ICML 2023Learning Globally Smooth Functions on Manifolds
20. ICML 2023Learning Preconditioners for Conjugate Gradient PDE Solvers
21. ICML 2023Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial Optimization
22. ICML 2023On Many-Actions Policy Gradient
23. ICML 2023On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization
24. ICML 2023On the Privacy-Robustness-Utility Trilemma in Distributed Learning
25. ICML 2023On Uni-Modal Feature Learning in Supervised Multi-Modal Learning
26. ICML 2023PixelAsParam: A Gradient View on Diffusion Sampling with Guidance
27. ICML 2023Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons
28. ICML 2023Provably Invariant Learning without Domain Information
29. ICML 2023Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL
30. ICML 2023QASA: Advanced Question Answering on Scientific Articles
31. ICML 2023Rethinking Weak Supervision in Helping Contrastive Learning
32. ICML 2023StriderNet: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes
33. ICML 2023Theoretical Bounds on the Network Community Profile from Low-rank Semi-definite Programming
34. ICML 2023Towards Robust Graph Incremental Learning on Evolving Graphs
35. ICML 2023Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression

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。