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 426 篇，第 3 / 9 页

101. ICLR 2026Multi-state Protein Design with DynamicMPNN
102. ICLR 2026New Hybrid Fine-Tuning Paradigm for LLMs: Algorithm Design and Convergence Analysis Framework
103. ICLR 2026Nonparametric Teaching of Attention Learners
104. ICLR 2026On the Design of One-step Diffusion via Shortcutting Flow Paths
105. ICLR 2026On the Mechanisms of Collaborative Learning in VAE Recommenders
106. ICLR 2026OSIRIS: Bridging Analog Circuit Design and Machine Learning with Scalable Dataset Generation
107. ICLR 2026Revisiting Nonstationary Kernel Design for Multi-Output Gaussian Processes
108. ICLR 2026Riemannian Variational Flow Matching for Material and Protein Design
109. ICLR 2026Scaling Bayesian Experimental Design to High-Dimensions with Information-Guided Diffusion
110. ICLR 2026SEED-SET: Scalable Evolving Experimental Design for System-level Ethical Testing
111. ICLR 2026Short Window Attention Enables Long-Term Memorization
112. ICLR 2026Si-GT: Fast Interconnect Signal Integrity Analysis for Integrated Circuit Design via Graph Transformers
113. ICLR 2026T1: One-to-One Channel-Head Binding for Multivariate Time-Series Imputation
114. ICLR 2026TINY BUT MIGHTY: A SOFTWARE-HARDWARE CO- DESIGN APPROACH FOR EFFICIENT MULTIMODAL IN- FERENCE ON BATTERY-POWERED SMALL DEVICES
115. ICLR 2026Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank Extension
116. ICLR 2026Towards Safe and Optimal Online Bidding: A Modular Look-ahead Lyapunov Framework
117. ICLR 2026Towards Strategic Persuasion with Language Models
118. ICLR 2026Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
119. ICLR 2026Two (narrow) heads are better than (an arbitrarily wide) one
120. ICLR 2026Understanding Routing Mechanism in Mixture-of-Experts Language Models
121. ICLR 2026Understanding Task Vectors in In-Context Learning: Emergence, Functionality, and Limitations
122. ICLR 2026Understanding the Implicit Biases of Design Choices for Time Series Foundation Models
123. ICLR 2026Unveiling the Mechanism of Continuous Representation Full-Waveform Inversion: A Wave Based Neural Tangent Kernel Framework
124. ICML 2026$\texttt{ShaplEIG}$: Bayesian Experimental Design for Shapley Value Estimation
125. ICML 2026$A_2$DEPT: Large Language Model–Driven Automated Algorithm Design via Evolutionary Program Trees
126. ICML 2026A General Neural Backbone for Mixed-Integer Linear Optimization via Dual Attention
127. ICML 2026A Unified Sparse Attention via Multi-Granularity Compression
128. ICML 2026Activation with Intrinsic-Extrinsic Consensus
129. ICML 2026Adaptive Querying with AI Persona Priors
130. ICML 2026Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention
131. ICML 2026AgentExpt: Automating AI Experiment Design with LLM-based Resource Retrieval Agent
132. ICML 2026Allocating Variance to Maximize Expectation
133. ICML 2026Anatomy of Massive Activations and Attention Sinks
134. ICML 2026Asymptotic Optimality of the High-Dimensional Gaussian Mechanism and Improved Low-Dimensional Mechanisms for Differential Privacy
135. ICML 2026Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse
136. ICML 2026Autobidding Auctions with LLM-Powered Creatives
137. ICML 2026Axiomatic Atlas: A Prescriptive Framework for Neural Architecture Design
138. ICML 2026Balancing Fidelity and Diversity in Diffusion Models via Symmetric Attention Decomposition: Hopfield Perspective
139. ICML 2026Breaking the Echo Chamber: A Dynamic Ensemble Pruning Perspective on MoE
140. ICML 2026Brep2Shape: Boundary and Shape Representation Alignment via Self-supervised Transformers
141. ICML 2026Budget-Feasible Mechanisms for Submodular Welfare Maximization in Procurement Auctions
142. ICML 2026CAMP: Coherent Alignment of Multimodal Prototypes for Explainable Complementary Learning
143. ICML 2026Chain-of-Thought Gradient Descent
144. ICML 2026Co-Generative De Novo Functional Protein Design
145. ICML 2026Constrained Bayesian Experimental Design via Online Planning
146. ICML 2026Contrastive Geometric Learning Unlocks Unified Structure- and Ligand-Based Drug Design
147. ICML 2026Decoupling The "What" and "Where" With Polar Coordinate Positional Embedding
148. ICML 2026Deep Incentive Design with Differentiable Equilibrium Blocks
149. ICML 2026Demystifying Action Space Design for Robotic Manipulation Policies
150. ICML 2026Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic Coupling

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。