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 295 篇，第 3 / 6 页

101. ICML 2026RTInfer: Real-Time Inference of Multiple DNNs on Edge GPUs
102. ICML 2026RulePlanner: All-in-One Reinforcement Learner for Unifying Design Rules in 3D Floorplanning
103. ICML 2026Selling Data as a Digital Good with Scaling Valuations
104. ICML 2026SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm
105. ICML 2026SlideSparse: Fast and Flexible (2N-2):2N Structured Sparsity
106. ICML 2026Softplus Attention with Re-weighting Boosts Length Extrapolation in Large Language Models
107. ICML 2026Sparser Block-Sparse Attention via Token Permutation
108. ICML 2026Spherical SO(3) Equivariant Local Attention
109. ICML 2026SpikeNet: Sparse Spike-Driven Mask Vector Transformer for Energy-Efficient and Stable Spiking Point Cloud Processing
110. ICML 2026Stability-Aware Feature Design for Robust Watermark Detection in Machine-Generated Text
111. ICML 2026Steering Large Language Models through the DMTA Cycle: Structure-Based Drug Design via Knowledge-Driven Bi-Level Thompson Sampling
112. ICML 2026Stop Training for the Worst: Progressive Unmasking Accelerates Masked Diffusion Training
113. ICML 2026SwitchCraft: A Programmatic Framework for Designing State-Switching Proteins
114. ICML 2026Test-Time Training with KV Binding Is Secretly Linear Attention
115. ICML 2026The Geometric Origin of Grokking: Accelerating Generalization via Active Structural Reorganization
116. ICML 2026The Role of Target Update Frequencies in Q-Learning
117. ICML 2026Towards Docking-oriented De Novo Ligand Design via Gradient Inversion
118. ICML 2026Towards Understanding Massive Activations in Attention Sink Mechanism
119. ICML 2026TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning
120. ICML 2026Tractable Expected Information Gains for Exponential Family Posteriors
121. ICML 2026Transformers with RL or SFT Provably Learn Sparse Boolean Functions, But Differently
122. ICML 2026Tucker Attention: A generalization of approximate attention mechanisms
123. ICML 2026Universal Approximation with Softmax Attention
124. ICML 2026Universal Representation of Generalized Convex Functions and their Gradients
125. ICML 2026Unveiling the Role of Data Uncertainty in Tabular Deep Learning
126. ICML 2026Welfare-Optimal Classification with Accuracy Auctions
127. ICML 2026WildCat: Near-Linear Attention in Theory and Practice
128. ICML 2026You Need Better Attention Priors
129. ICML 2025ADIOS: Antibody Development via Opponent Shaping
130. ICML 2025AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N
131. ICML 2025An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks
132. ICML 2025Backdoor Attacks in Token Selection of Attention Mechanism
133. ICML 2025BAnG: Bidirectional Anchored Generation for Conditional RNA Design
134. ICML 2025Benign Overfitting in Token Selection of Attention Mechanism
135. ICML 2025CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention
136. ICML 2025Collaborative Mean Estimation Among Heterogeneous Strategic Agents: Individual Rationality, Fairness, and Truthful Contribution
137. ICML 2025Contract Design Under Approximate Best Responses
138. ICML 2025Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers
139. ICML 2025CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features
140. ICML 2025Data-driven Design of Randomized Control Trials with Guaranteed Treatment Effects
141. ICML 2025Decomposition of Graphic Design with Unified Multimodal Model
142. ICML 2025DeepCrossAttention: Supercharging Transformer Residual Connections
143. ICML 2025Distributionally Robust Active Learning for Gaussian Process Regression
144. ICML 2025Diversity By Design: Leveraging Distribution Matching for Offline Model-Based Optimization
145. ICML 2025DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing
146. ICML 2025Domain-Adapted Diffusion Model for PROTAC Linker Design Through the Lens of Density Ratio in Chemical Space
147. ICML 2025Efficient and Separate Authentication Image Steganography Network
148. ICML 2025Elucidating the Design Space of Multimodal Protein Language Models
149. ICML 2025Empirical Design in Reinforcement Learning
150. ICML 2025Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss

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。