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 200 篇，第 2 / 4 页

51. ICLR 2024Independent-Set Design of Experiments for Estimating Treatment and Spillover Effects under Network Interference
52. ICLR 2024Intriguing Properties of Data Attribution on Diffusion Models
53. ICLR 2024KW-Design: Pushing the Limit of Protein Design via Knowledge Refinement
54. ICLR 2024Learning to design protein-protein interactions with enhanced generalization
55. ICLR 2024Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design
56. ICLR 2024Local Search GFlowNets
57. ICLR 2024Online Information Acquisition: Hiring Multiple Agents
58. ICLR 2024Privacy Amplification for Matrix Mechanisms
59. ICLR 2024Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
60. ICLR 2024RDesign: Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design
61. ICLR 2024RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with Anomalies
62. ICLR 2024Scalable Neural Network Kernels
63. ICLR 2024Stochastic Modified Equations and Dynamics of Dropout Algorithm
64. ICLR 2024Unraveling the Key Components of OOD Generalization via Diversification
65. ICML 2024A Contextual Combinatorial Bandit Approach to Negotiation
66. ICML 2024Active Adaptive Experimental Design for Treatment Effect Estimation with Covariate Choice
67. ICML 2024Adaptive Online Experimental Design for Causal Discovery
68. ICML 2024Antibody Design Using a Score-based Diffusion Model Guided by Evolutionary, Physical and Geometric Constraints
69. ICML 2024Bayesian Design Principles for Offline-to-Online Reinforcement Learning
70. ICML 2024Beyond the Calibration Point: Mechanism Comparison in Differential Privacy
71. ICML 2024Bringing Motion Taxonomies to Continuous Domains via GPLVM on Hyperbolic manifolds
72. ICML 2024CarbonNovo: Joint Design of Protein Structure and Sequence Using a Unified Energy-based Model
73. ICML 2024Characterizing ResNet's Universal Approximation Capability
74. ICML 2024Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design
75. ICML 2024Controlled Decoding from Language Models
76. ICML 2024Data-free Neural Representation Compression with Riemannian Neural Dynamics
77. ICML 2024Don’t Label Twice: Quantity Beats Quality when Comparing Binary Classifiers on a Budget
78. ICML 2024DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design
79. ICML 2024Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits
80. ICML 2024Environment Design for Inverse Reinforcement Learning
81. ICML 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model
82. ICML 2024Faithfulness Measurable Masked Language Models
83. ICML 2024Full-Atom Peptide Design based on Multi-modal Flow Matching
84. ICML 2024Fundamental Limitations of Alignment in Large Language Models
85. ICML 2024Generative Enzyme Design Guided by Functionally Important Sites and Small-Molecule Substrates
86. ICML 2024GeoAB: Towards Realistic Antibody Design and Reliable Affinity Maturation
87. ICML 2024Harmonic Self-Conditioned Flow Matching for joint Multi-Ligand Docking and Binding Site Design
88. ICML 2024How Does Goal Relabeling Improve Sample Efficiency?
89. ICML 2024How Interpretable Are Interpretable Graph Neural Networks?
90. ICML 2024How Private are DP-SGD Implementations?
91. ICML 2024ILILT: Implicit Learning of Inverse Lithography Technologies
92. ICML 2024Implicit Regularization in Feedback Alignment Learning Mechanisms for Neural Networks
93. ICML 2024Improving Sharpness-Aware Minimization by Lookahead
94. ICML 2024Incentivized Learning in Principal-Agent Bandit Games
95. ICML 2024KernelWarehouse: Rethinking the Design of Dynamic Convolution
96. ICML 2024Learning Linear Block Error Correction Codes
97. ICML 2024Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace Recovery
98. ICML 2024Mechanistic Design and Scaling of Hybrid Architectures
99. ICML 2024MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space
100. ICML 2024More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms

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。