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 182 篇，第 3 / 4 页

101. ICLR 2025Mechanism and Emergence of Stacked Attention Heads in Multi-Layer Transformers
102. ICLR 2025Neural networks on Symmetric Spaces of Noncompact Type
103. ICLR 2025On Rollouts in Model-Based Reinforcement Learning
104. ICLR 2025Optimality of Matrix Mechanism on $\ell_p^p$-metric
105. ICLR 2025ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization
106. ICLR 2025OSDA Agent: Leveraging Large Language Models for De Novo Design of Organic Structure Directing Agents
107. ICLR 2025Policy Design in Long-run Welfare Dynamics
108. ICLR 2025Private Mechanism Design via Quantile Estimation
109. ICLR 2025Real-time design of architectural structures with differentiable mechanics and neural networks
110. ICLR 2025Reframing Structure-Based Drug Design Model Evaluation via Metrics Correlated to Practical Needs
111. ICLR 2025Regulatory DNA Sequence Design with Reinforcement Learning
112. ICLR 2025Revisiting a Design Choice in Gradient Temporal Difference Learning
113. ICLR 2025Scaling up the Banded Matrix Factorization Mechanism for Large Scale Differentially Private ML
114. ICLR 2025Self-Improvement in Language Models: The Sharpening Mechanism
115. ICLR 2025Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training
116. ICLR 2025Simple Guidance Mechanisms for Discrete Diffusion Models
117. ICLR 2025Steering Protein Family Design through Profile Bayesian Flow
118. ICLR 2025SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraints
119. ICLR 2025Systematic Outliers in Large Language Models
120. ICLR 2025T2V-Turbo-v2: Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance Design
121. ICLR 2025Three Mechanisms of Feature Learning in a Linear Network
122. ICLR 2025Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search
123. ICLR 2025Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos
124. ICLR 2024Adaptive deep spiking neural network with global-local learning via balanced excitatory and inhibitory mechanism
125. ICLR 2024Adaptive Instrument Design for Indirect Experiments
126. ICLR 2024Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation
127. ICLR 2024CircuitNet 2.0: An Advanced Dataset for Promoting Machine Learning Innovations in Realistic Chip Design Environment
128. ICLR 2024De novo Protein Design Using Geometric Vector Field Networks
129. ICLR 2024Debiasing Attention Mechanism in Transformer without Demographics
130. ICLR 2024Elucidating the design space of classifier-guided diffusion generation
131. ICLR 2024Graphical Multioutput Gaussian Process with Attention
132. ICLR 2024GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers
133. ICLR 2024Incentive-Aware Federated Learning with Training-Time Model Rewards
134. ICLR 2024Incentivized Truthful Communication for Federated Bandits
135. ICLR 2024Independent-Set Design of Experiments for Estimating Treatment and Spillover Effects under Network Interference
136. ICLR 2024Intriguing Properties of Data Attribution on Diffusion Models
137. ICLR 2024KW-Design: Pushing the Limit of Protein Design via Knowledge Refinement
138. ICLR 2024Learning to design protein-protein interactions with enhanced generalization
139. ICLR 2024Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design
140. ICLR 2024Local Search GFlowNets
141. ICLR 2024Online Information Acquisition: Hiring Multiple Agents
142. ICLR 2024Privacy Amplification for Matrix Mechanisms
143. ICLR 2024Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
144. ICLR 2024RDesign: Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design
145. ICLR 2024RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with Anomalies
146. ICLR 2024Scalable Neural Network Kernels
147. ICLR 2024Stochastic Modified Equations and Dynamics of Dropout Algorithm
148. ICLR 2024Unraveling the Key Components of OOD Generalization via Diversification
149. ICLR 2023AANG : Automating Auxiliary Learning
150. ICLR 2023CktGNN: Circuit Graph Neural Network for Electronic Design Automation

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。