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 166 篇，第 3 / 4 页

101. CVPR 2024Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers
102. CVPR 2024Behind the Veil: Enhanced Indoor 3D Scene Reconstruction with Occluded Surfaces Completion
103. CVPR 2024BoQ: A Place is Worth a Bag of Learnable Queries
104. CVPR 2024Byzantine-robust Decentralized Federated Learning via Dual-domain Clustering and Trust Bootstrapping
105. CVPR 2024CAMixerSR: Only Details Need More "Attention"
106. CVPR 2024Capturing Closely Interacted Two-Person Motions with Reaction Priors
107. CVPR 2024Circuit Design and Efficient Simulation of Quantum Inner Product and Empirical Studies of Its Effect on Near-Term Hybrid Quantum-Classic Machine Learning
108. CVPR 2024Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods
109. CVPR 2024Desigen: A Pipeline for Controllable Design Template Generation
110. CVPR 2024Dexterous Grasp Transformer
111. CVPR 2024Discontinuity-preserving Normal Integration with Auxiliary Edges
112. CVPR 2024Discriminative Pattern Calibration Mechanism for Source-Free Domain Adaptation
113. CVPR 2024Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training
114. CVPR 2024Generalized Event Cameras
115. CVPR 2024HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses
116. CVPR 2024Improving Depth Completion via Depth Feature Upsampling
117. CVPR 2024InceptionNeXt: When Inception Meets ConvNeXt
118. CVPR 2024Language-guided Image Reflection Separation
119. CVPR 2024Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach
120. CVPR 2024LPSNet: End-to-End Human Pose and Shape Estimation with Lensless Imaging
121. CVPR 2024MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images
122. CVPR 2024MLP Can Be A Good Transformer Learner
123. CVPR 2024Monocular Identity-Conditioned Facial Reflectance Reconstruction
124. CVPR 2024NAPGuard: Towards Detecting Naturalistic Adversarial Patches
125. CVPR 2024NC-SDF: Enhancing Indoor Scene Reconstruction Using Neural SDFs with View-Dependent Normal Compensation
126. CVPR 2024PBWR: Parametric-Building-Wireframe Reconstruction from Aerial LiDAR Point Clouds
127. CVPR 2024Point Transformer V3: Simpler Faster Stronger
128. CVPR 2024ProMotion: Prototypes As Motion Learners
129. CVPR 2024Rethinking Generalizable Face Anti-spoofing via Hierarchical Prototype-guided Distribution Refinement in Hyperbolic Space
130. CVPR 2024Rewrite the Stars
131. CVPR 2024SAI3D: Segment Any Instance in 3D Scenes
132. CVPR 2024SAOR: Single-View Articulated Object Reconstruction
133. CVPR 2024SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design
134. CVPR 2024StraightPCF: Straight Point Cloud Filtering
135. CVPR 2024SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting
136. CVPR 2024Unsegment Anything by Simulating Deformation
137. CVPR 2024V?: Guided Visual Search as a Core Mechanism in Multimodal LLMs
138. CVPR 2023Achieving a Better Stability-Plasticity Trade-Off via Auxiliary Networks in Continual Learning
139. CVPR 2023BASiS: Batch Aligned Spectral Embedding Space
140. CVPR 2023Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution
141. CVPR 2023Coaching a Teachable Student
142. CVPR 2023DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network
143. CVPR 2023DSVT: Dynamic Sparse Voxel Transformer With Rotated Sets
144. CVPR 2023DynaFed: Tackling Client Data Heterogeneity With Global Dynamics
145. CVPR 2023Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization
146. CVPR 2023F2-NeRF: Fast Neural Radiance Field Training With Free Camera Trajectories
147. CVPR 2023Fine-Grained Classification With Noisy Labels
148. CVPR 2023Fine-Grained Face Swapping via Regional GAN Inversion
149. CVPR 2023Ham2Pose: Animating Sign Language Notation Into Pose Sequences
150. CVPR 2023Heterogeneous Continual Learning

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。