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 2 / 4 页

51. ICLR 2026Scaling Bayesian Experimental Design to High-Dimensions with Information-Guided Diffusion
52. ICLR 2026SEED-SET: Scalable Evolving Experimental Design for System-level Ethical Testing
53. ICLR 2026Short Window Attention Enables Long-Term Memorization
54. ICLR 2026Si-GT: Fast Interconnect Signal Integrity Analysis for Integrated Circuit Design via Graph Transformers
55. ICLR 2026T1: One-to-One Channel-Head Binding for Multivariate Time-Series Imputation
56. ICLR 2026TINY BUT MIGHTY: A SOFTWARE-HARDWARE CO- DESIGN APPROACH FOR EFFICIENT MULTIMODAL IN- FERENCE ON BATTERY-POWERED SMALL DEVICES
57. ICLR 2026Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank Extension
58. ICLR 2026Towards Safe and Optimal Online Bidding: A Modular Look-ahead Lyapunov Framework
59. ICLR 2026Towards Strategic Persuasion with Language Models
60. ICLR 2026Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
61. ICLR 2026Two (narrow) heads are better than (an arbitrarily wide) one
62. ICLR 2026Understanding Routing Mechanism in Mixture-of-Experts Language Models
63. ICLR 2026Understanding Task Vectors in In-Context Learning: Emergence, Functionality, and Limitations
64. ICLR 2026Understanding the Implicit Biases of Design Choices for Time Series Foundation Models
65. ICLR 2026Unveiling the Mechanism of Continuous Representation Full-Waveform Inversion: A Wave Based Neural Tangent Kernel Framework
66. ICLR 2025A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention
67. ICLR 2025AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning
68. ICLR 2025Agree to Disagree: Demystifying Homogeneous Deep Ensembles through Distributional Equivalence
69. ICLR 2025Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis
70. ICLR 2025Automated Design of Agentic Systems
71. ICLR 2025Bayesian Experimental Design Via Contrastive Diffusions
72. ICLR 2025Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks
73. ICLR 2025BodyGen: Advancing Towards Efficient Embodiment Co-Design
74. ICLR 2025Charting the Design Space of Neural Graph Representations for Subgraph Matching
75. ICLR 2025Clique Number Estimation via Differentiable Functions of Adjacency Matrix Permutations
76. ICLR 2025Concept Bottleneck Language Models For Protein Design
77. ICLR 2025Data Distillation for extrapolative protein design through exact preference optimization
78. ICLR 2025DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale
79. ICLR 2025DICE: Data Influence Cascade in Decentralized Learning
80. ICLR 2025Do Stochastic, Feel Noiseless: Stable Stochastic Optimization via a Double Momentum Mechanism
81. ICLR 2025Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders
82. ICLR 2025Efficient Biological Data Acquisition through Inference Set Design
83. ICLR 2025EVA: Geometric Inverse Design for Fast Protein Motif-Scaffolding with Coupled Flow
84. ICLR 2025Exploring channel distinguishability in local neighborhoods of the model space in quantum neural networks
85. ICLR 2025Fast Uncovering of Protein Sequence Diversity from Structure
86. ICLR 2025Flow-based Variational Mutual Information: Fast and Flexible Approximations
87. ICLR 2025Fragment and Geometry Aware Tokenization of Molecules for Structure-Based Drug Design Using Language Models
88. ICLR 2025FreeCG: Free the Design Space of Clebsch-Gordan Transform for Machine Learning Force Fields
89. ICLR 2025Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective
90. ICLR 2025Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and Attention
91. ICLR 2025gRNAde: Geometric Deep Learning for 3D RNA inverse design
92. ICLR 2025Hierarchically Encapsulated Representation for Protocol Design in Self-Driving Labs
93. ICLR 2025Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning
94. ICLR 2025IgGM: A Generative Model for Functional Antibody and Nanobody Design
95. ICLR 2025Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface
96. ICLR 2025Interference Among First-Price Pacing Equilibria: A Bias and Variance Analysis
97. ICLR 2025LASeR: Towards Diversified and Generalizable Robot Design with Large Language Models
98. ICLR 2025Learning to engineer protein flexibility
99. ICLR 2025Look Before You Leap: Universal Emergent Mechanism for Retrieval in Language Models
100. ICLR 2025MaestroMotif: Skill Design from Artificial Intelligence Feedback

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。