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 271 篇，第 2 / 6 页

51. ICLR 2025Concept Bottleneck Language Models For Protein Design
52. ICLR 2025Data Distillation for extrapolative protein design through exact preference optimization
53. ICLR 2025DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale
54. ICLR 2025DICE: Data Influence Cascade in Decentralized Learning
55. ICLR 2025Do Stochastic, Feel Noiseless: Stable Stochastic Optimization via a Double Momentum Mechanism
56. ICLR 2025Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders
57. ICLR 2025Efficient Biological Data Acquisition through Inference Set Design
58. ICLR 2025EVA: Geometric Inverse Design for Fast Protein Motif-Scaffolding with Coupled Flow
59. ICLR 2025Exploring channel distinguishability in local neighborhoods of the model space in quantum neural networks
60. ICLR 2025Fast Uncovering of Protein Sequence Diversity from Structure
61. ICLR 2025Flow-based Variational Mutual Information: Fast and Flexible Approximations
62. ICLR 2025Fragment and Geometry Aware Tokenization of Molecules for Structure-Based Drug Design Using Language Models
63. ICLR 2025FreeCG: Free the Design Space of Clebsch-Gordan Transform for Machine Learning Force Fields
64. ICLR 2025Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective
65. ICLR 2025Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and Attention
66. ICLR 2025gRNAde: Geometric Deep Learning for 3D RNA inverse design
67. ICLR 2025Hierarchically Encapsulated Representation for Protocol Design in Self-Driving Labs
68. ICLR 2025Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning
69. ICLR 2025IgGM: A Generative Model for Functional Antibody and Nanobody Design
70. ICLR 2025Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface
71. ICLR 2025Interference Among First-Price Pacing Equilibria: A Bias and Variance Analysis
72. ICLR 2025LASeR: Towards Diversified and Generalizable Robot Design with Large Language Models
73. ICLR 2025Learning to engineer protein flexibility
74. ICLR 2025Look Before You Leap: Universal Emergent Mechanism for Retrieval in Language Models
75. ICLR 2025MaestroMotif: Skill Design from Artificial Intelligence Feedback
76. ICLR 2025Mechanism and Emergence of Stacked Attention Heads in Multi-Layer Transformers
77. ICLR 2025Neural networks on Symmetric Spaces of Noncompact Type
78. ICLR 2025On Rollouts in Model-Based Reinforcement Learning
79. ICLR 2025Optimality of Matrix Mechanism on $\ell_p^p$-metric
80. ICLR 2025ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization
81. ICLR 2025OSDA Agent: Leveraging Large Language Models for De Novo Design of Organic Structure Directing Agents
82. ICLR 2025Policy Design in Long-run Welfare Dynamics
83. ICLR 2025Private Mechanism Design via Quantile Estimation
84. ICLR 2025Real-time design of architectural structures with differentiable mechanics and neural networks
85. ICLR 2025Reframing Structure-Based Drug Design Model Evaluation via Metrics Correlated to Practical Needs
86. ICLR 2025Regulatory DNA Sequence Design with Reinforcement Learning
87. ICLR 2025Revisiting a Design Choice in Gradient Temporal Difference Learning
88. ICLR 2025Scaling up the Banded Matrix Factorization Mechanism for Large Scale Differentially Private ML
89. ICLR 2025Self-Improvement in Language Models: The Sharpening Mechanism
90. ICLR 2025Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training
91. ICLR 2025Simple Guidance Mechanisms for Discrete Diffusion Models
92. ICLR 2025Steering Protein Family Design through Profile Bayesian Flow
93. ICLR 2025SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraints
94. ICLR 2025Systematic Outliers in Large Language Models
95. ICLR 2025T2V-Turbo-v2: Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance Design
96. ICLR 2025Three Mechanisms of Feature Learning in a Linear Network
97. ICLR 2025Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search
98. ICLR 2025Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos
99. ICML 2025ADIOS: Antibody Development via Opponent Shaping
100. ICML 2025AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N

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。