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 3 / 6 页

101. ICML 2025An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks
102. ICML 2025Backdoor Attacks in Token Selection of Attention Mechanism
103. ICML 2025BAnG: Bidirectional Anchored Generation for Conditional RNA Design
104. ICML 2025Benign Overfitting in Token Selection of Attention Mechanism
105. ICML 2025CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention
106. ICML 2025Collaborative Mean Estimation Among Heterogeneous Strategic Agents: Individual Rationality, Fairness, and Truthful Contribution
107. ICML 2025Contract Design Under Approximate Best Responses
108. ICML 2025Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers
109. ICML 2025CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features
110. ICML 2025Data-driven Design of Randomized Control Trials with Guaranteed Treatment Effects
111. ICML 2025Decomposition of Graphic Design with Unified Multimodal Model
112. ICML 2025DeepCrossAttention: Supercharging Transformer Residual Connections
113. ICML 2025Distributionally Robust Active Learning for Gaussian Process Regression
114. ICML 2025Diversity By Design: Leveraging Distribution Matching for Offline Model-Based Optimization
115. ICML 2025DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing
116. ICML 2025Domain-Adapted Diffusion Model for PROTAC Linker Design Through the Lens of Density Ratio in Chemical Space
117. ICML 2025Efficient and Separate Authentication Image Steganography Network
118. ICML 2025Elucidating the Design Space of Multimodal Protein Language Models
119. ICML 2025Empirical Design in Reinforcement Learning
120. ICML 2025Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss
121. ICML 2025Equivariant Polynomial Functional Networks
122. ICML 2025ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans
123. ICML 2025Fraud-Proof Revenue Division on Subscription Platforms
124. ICML 2025Heads up! Large Language Models Can Perform Tasks Without Your Instruction via Selective Attention Head Masking
125. ICML 2025Improved Off-policy Reinforcement Learning in Biological Sequence Design
126. ICML 2025In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention
127. ICML 2025Integer Programming for Generalized Causal Bootstrap Designs
128. ICML 2025Learning to Generate Projections for Reducing Dimensionality of Heterogeneous Linear Programming Problems
129. ICML 2025LipsNet++: Unifying Filter and Controller into a Policy Network
130. ICML 2025LLM Enhancers for GNNs: An Analysis from the Perspective of Causal Mechanism Identification
131. ICML 2025LLM-Augmented Chemical Synthesis and Design Decision Programs
132. ICML 2025Mechanisms of Projective Composition of Diffusion Models
133. ICML 2025Mind the Gap: a Spectral Analysis of Rank Collapse and Signal Propagation in Attention Layers
134. ICML 2025Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design
135. ICML 2025MVA: Linear Attention with High-order Query-Keys Integration and Multi-level Vocabulary Decomposition
136. ICML 2025MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design
137. ICML 2025Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics Discovery
138. ICML 2025On the Emergence of Position Bias in Transformers
139. ICML 2025On the Statistical Mechanisms of Distributional Compositional Generalization
140. ICML 2025Optimal Auction Design in the Joint Advertising
141. ICML 2025Optimal Survey Design for Private Mean Estimation
142. ICML 2025Optimizing Social Network Interventions via Hypergradient-Based Recommender System Design
143. ICML 2025P(all-atom) Is Unlocking New Path For Protein Design
144. ICML 2025Peri-LN: Revisiting Normalization Layer in the Transformer Architecture
145. ICML 2025Piloting Structure-Based Drug Design via Modality-Specific Optimal Schedule
146. ICML 2025Policy Design for Two-sided Platforms with Participation Dynamics
147. ICML 2025PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design
148. ICML 2025Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All
149. ICML 2025Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents
150. ICML 2025Probabilistic Factorial Experimental Design for Combinatorial Interventions

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。