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 67 篇，第 2 / 2 页

51. ICML 2024Prompting a Pretrained Transformer Can Be a Universal Approximator
52. ICML 2024Receptive Fields As Experts in Convolutional Neural Architectures
53. ICML 2024Refining Minimax Regret for Unsupervised Environment Design
54. ICML 2024Rényi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration via Shift Reduction Lemmas
55. ICML 2024Replicable Learning of Large-Margin Halfspaces
56. ICML 2024RNAFlow: RNA Structure & Sequence Design via Inverse Folding-Based Flow Matching
57. ICML 2024Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup
58. ICML 2024Self-attention Networks Localize When QK-eigenspectrum Concentrates
59. ICML 2024Sliding Down the Stairs: How Correlated Latent Variables Accelerate Learning with Neural Networks
60. ICML 2024Sparser, Better, Deeper, Stronger: Improving Static Sparse Training with Exact Orthogonal Initialization
61. ICML 2024Stochastic Bandits with ReLU Neural Networks
62. ICML 2024Structure-based drug design by denoising voxel grids
63. ICML 2024Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products
64. ICML 2024SurfPro: Functional Protein Design Based on Continuous Surface
65. ICML 2024The Pitfalls of Next-Token Prediction
66. ICML 2024Unmasking Vulnerabilities: Cardinality Sketches under Adaptive Inputs
67. ICML 2024Unsupervised Representation Learning of Brain Activity via Bridging Voxel Activity and Functional Connectivity

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。