机制设计论文趋势 2023–2026

主要结论

• 机制设计论文从 2023 年的 140 篇增长到 2026 年的 426 篇，三年间扩大到约 3.0 倍。
• NeurIPS 是发机制设计论文最多的会议，2023–2026 年共 394 篇，占四个会议总量的 38%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 5 篇增至 2026 年的 42 篇。
• 在「博弈与规划」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的经典规划是 3.3 倍，机制设计是 3.0 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 2026A Generalized Tikhonov Layer for Interpretable-by-design Graph Neural Networks
• ICML 2026Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention
• ICLR 2026Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation
• CVPR 2026FEAT Fashion Editing and Try-On from Any Design
• NeurIPS 2025A Closer Look at Graph Transformers: Cross-Aggregation and Beyond
• ICML 2025Benign Overfitting in Token Selection of Attention Mechanism
• ICLR 2025AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning
• CVPR 2025A Selective Re-learning Mechanism for Hyperspectral Fusion Imaging
• NeurIPS 2024AFBench: A Large-scale Benchmark for Airfoil Design
• ICML 2024CarbonNovo: Joint Design of Protein Structure and Sequence Using a Unified Energy-based Model
• ICLR 2024Adaptive Instrument Design for Indirect Experiments
• CVPR 2024InceptionNeXt: When Inception Meets ConvNeXt
• NeurIPS 2023An Optimal and Scalable Matrix Mechanism for Noisy Marginals under Convex Loss Functions
• ICML 2023AbODE: Ab initio antibody design using conjoined ODEs
• ICLR 2023Conditional Antibody Design as 3D Equivariant Graph Translation
• CVPR 2023Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization
• NeurIPS 2026A Unified Framework for Uniform-Price Resource Allocation Mechanisms
• ICML 2026Anatomy of Massive Activations and Attention Sinks
• ICLR 2026How Muon’s Spectral Design Benefits Generalization: A Study on Imbalanced Data
• CVPR 2026Parallax to Align Them All An OmniParallax Attention Mechanism for

全部机制设计论文

共 35 篇，第 1 / 1 页

1. ICML 2023"Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts
2. ICML 2023AbODE: Ab initio antibody design using conjoined ODEs
3. ICML 2023Are labels informative in semi-supervised learning? Estimating and leveraging the missing-data mechanism.
4. ICML 2023Bayesian Design Principles for Frequentist Sequential Learning
5. ICML 2023CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design
6. ICML 2023Conformalization of Sparse Generalized Linear Models
7. ICML 2023Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgets
8. ICML 2023Differentiable Multi-Target Causal Bayesian Experimental Design
9. ICML 2023DiscoBAX - Discovery of optimal intervention sets in genomic experiment design
10. ICML 2023DRew: Dynamically Rewired Message Passing with Delay
11. ICML 2023End-to-End Full-Atom Antibody Design
12. ICML 2023Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction
13. ICML 2023Generalized Implicit Follow-The-Regularized-Leader
14. ICML 2023Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement
15. ICML 2023Hidden Symmetries of ReLU Networks
16. ICML 2023Importance Weighted Expectation-Maximization for Protein Sequence Design
17. ICML 2023Improving Expert Predictions with Conformal Prediction
18. ICML 2023IRNeXt: Rethinking Convolutional Network Design for Image Restoration
19. ICML 2023Last Switch Dependent Bandits with Monotone Payoff Functions
20. ICML 2023Learning Subpocket Prototypes for Generalizable Structure-based Drug Design
21. ICML 2023Learning to Bid in Repeated First-Price Auctions with Budgets
22. ICML 2023Model-Free Robust Average-Reward Reinforcement Learning
23. ICML 2023Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning
24. ICML 2023Online Mechanism Design for Information Acquisition
25. ICML 2023Pricing Experimental Design: Causal Effect, Expected Revenue and Tail Risk
26. ICML 2023Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design
27. ICML 2023Provable Reset-free Reinforcement Learning by No-Regret Reduction
28. ICML 2023SAAL: Sharpness-Aware Active Learning
29. ICML 2023Sequential Kernelized Independence Testing
30. ICML 2023Sequential Strategic Screening
31. ICML 2023Simplex Random Features
32. ICML 2023Symmetry-Aware Robot Design with Structured Subgroups
33. ICML 2023Task-specific experimental design for treatment effect estimation
34. ICML 2023Transformers Learn In-Context by Gradient Descent
35. ICML 2023Trapdoor Normalization with Irreversible Ownership Verification

常见问题

2023–2026 年四大会议一共有多少篇机制设计论文？

共 1,037 篇，按年份分别是 2023 年 140 篇、2024 年 200 篇、2025 年 271 篇、2026 年 426 篇。

NeurIPS 2026 有多少篇机制设计论文？

NeurIPS 2026 有 175 篇机制设计论文，上一届是 108 篇。

ICLR 2026 有多少篇机制设计论文？

ICLR 2026 有 65 篇机制设计论文，上一届是 58 篇。

ICML 2026 有多少篇机制设计论文？

ICML 2026 有 128 篇机制设计论文，上一届是 65 篇。

CVPR 2026 有多少篇机制设计论文？

CVPR 2026 有 58 篇机制设计论文，上一届是 40 篇。

哪个会议的机制设计论文最多？

NeurIPS，2023–2026 年共 394 篇。