混合专家论文趋势 2023–2026

MoE 路由与训练

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 904 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

混合专家论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202313816766236
20245524319119
202586595721223
2026757313246326

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

全部混合专家论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 354 篇，第 5 / 8 页

  1. NeurIPS 2024Once Read is Enough: Domain-specific Pretraining-free Language Models with Cluster-guided Sparse Experts for Long-tail Domain Knowledge
  2. NeurIPS 2024Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts
  3. NeurIPS 2024Personalized Federated Learning with Mixture of Models for Adaptive Prediction and Model Fine-Tuning
  4. NeurIPS 2024ProxyFusion: Face Feature Aggregation Through Sparse Experts
  5. NeurIPS 2024Robust Mixture Learning when Outliers Overwhelm Small Groups
  6. NeurIPS 2024Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
  7. NeurIPS 2024Smoothie: Label Free Language Model Routing
  8. NeurIPS 2024Spiking Transformer with Experts Mixture
  9. NeurIPS 2024Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning
  10. NeurIPS 2024SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention
  11. NeurIPS 2024Toward Efficient Inference for Mixture of Experts
  12. NeurIPS 2024Transcendence: Generative Models Can Outperform The Experts That Train Them
  13. NeurIPS 2024Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
  14. NeurIPS 2024Unchosen Experts Can Contribute Too: Unleashing MoE Models’ Power by Self-Contrast
  15. NeurIPS 2024Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE
  16. NeurIPS 2024Variational Distillation of Diffusion Policies into Mixture of Experts
  17. NeurIPS 2023[Re] Exploring the Role of Grammar and Word Choice in Bias Toward African American English (AAE) in Hate Speech Classification
  18. NeurIPS 2023[Re] Numerical influence of ReLU'(0) on backpropagation
  19. NeurIPS 2023[Re] On Explainability of Graph Neural Networks via Subgraph Explorations
  20. NeurIPS 2023[Re] On the Reproducibility of “FairCal: Fairness Calibration for Face Verification”
  21. NeurIPS 2023[Re] On the Reproducibility of CartoonX
  22. NeurIPS 2023[Re] Pure Noise to the Rescue of Insufficient Data
  23. NeurIPS 2023$\mathbf{\mathbb{E}^{FWI}}$: Multiparameter Benchmark Datasets for Elastic Full Waveform Inversion of Geophysical Properties
  24. NeurIPS 2023A benchmark of categorical encoders for binary classification
  25. NeurIPS 2023A Dataset of Relighted 3D Interacting Hands
  26. NeurIPS 2023A Dynamical System View of Langevin-Based Non-Convex Sampling
  27. NeurIPS 2023A Guide Through the Zoo of Biased SGD
  28. NeurIPS 2023A Massive Scale Semantic Similarity Dataset of Historical English
  29. NeurIPS 2023A normative theory of social conflict
  30. NeurIPS 2023Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness
  31. NeurIPS 2023Aiming towards the minimizers: fast convergence of SGD for overparametrized problems
  32. NeurIPS 2023Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception
  33. NeurIPS 2023An Empirical Investigation of the Role of Pre-training in Lifelong Learning
  34. NeurIPS 2023Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences
  35. NeurIPS 2023Bounded rationality in structured density estimation
  36. NeurIPS 2023Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information
  37. NeurIPS 2023Causal Effect Regularization: Automated Detection and Removal of Spurious Correlations
  38. NeurIPS 2023Characterization of Overfitting in Robust Multiclass Classification
  39. NeurIPS 2023Circuit as Set of Points
  40. NeurIPS 2023Classification of Heavy-tailed Features in High Dimensions: a Superstatistical Approach
  41. NeurIPS 2023Concentration analysis of multivariate elliptic diffusions
  42. NeurIPS 2023Convergence of Alternating Gradient Descent for Matrix Factorization
  43. NeurIPS 2023DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets
  44. NeurIPS 2023DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection
  45. NeurIPS 2023Demystifying Softmax Gating Function in Gaussian Mixture of Experts
  46. NeurIPS 2023Dense-Exponential Random Features: Sharp Positive Estimators of the Gaussian Kernel
  47. NeurIPS 2023Density of States Prediction of Crystalline Materials via Prompt-guided Multi-Modal Transformer
  48. NeurIPS 2023Differentiable and Stable Long-Range Tracking of Multiple Posterior Modes
  49. NeurIPS 2023Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching
  50. NeurIPS 2023Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick

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 查混合专家在 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": "mixture-of-experts"}

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混合专家论文？
共 904 篇，按年份分别是 2023 年 236 篇、2024 年 119 篇、2025 年 223 篇、2026 年 326 篇。
NeurIPS 2026 有多少篇混合专家论文？
NeurIPS 2026 有 75 篇混合专家论文，上一届是 86 篇。
ICLR 2026 有多少篇混合专家论文？
ICLR 2026 有 73 篇混合专家论文，上一届是 59 篇。
ICML 2026 有多少篇混合专家论文？
ICML 2026 有 132 篇混合专家论文，上一届是 57 篇。
CVPR 2026 有多少篇混合专家论文？
CVPR 2026 有 46 篇混合专家论文，上一届是 21 篇。
哪个会议的混合专家论文最多？
NeurIPS，2023–2026 年共 354 篇。

「优化与缩放」下的其他主题