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 65 篇，第 1 / 2 页

1. ICLR 2026A Brain-Inspired Gating Mechanism Unlocks Robust Computation in Spiking Neural Networks
2. ICLR 2026A Joint Diffusion Model with Pre-Trained Priors for RNA Sequence–Structure Co-Design
3. ICLR 2026Accelerated co-design of robots through morphological pretraining
4. ICLR 2026Activation Function Design Sustains Plasticity in Continual Learning
5. ICLR 2026AFD-INSTRUCTION: A Comprehensive Antibody Instruction Dataset with Functional Annotations for LLM-Based Understanding and Design
6. ICLR 2026An Information-Theoretical Framework For Optimizing Experimental Design To Distinguish Probabilistic Neural Codes
7. ICLR 2026ASIDE: Architectural Separation of Instructions and Data in Language Models
8. ICLR 2026AutoEP: LLMs-Driven Automation of Hyperparameter Evolution for Metaheuristic Algorithms
9. ICLR 2026Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation
10. ICLR 2026BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design
11. ICLR 2026BioBO: Biology-informed Bayesian Optimization for Perturbation Design
12. ICLR 2026Breaking the Correlation Plateau: On the Optimization and Capacity Limits of Attention-Based Regressors
13. ICLR 2026CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design
14. ICLR 2026Can Vision–Language Models Assess Graphic Design Aesthetics? A Benchmark, Evaluation, and Dataset Perspective.
15. ICLR 2026Composer: A Search Framework for Hybrid Neural Architecture Design
16. ICLR 2026Constrained Diffusion for Protein Design with Hard Structural Constraints
17. ICLR 2026CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Design
18. ICLR 2026Deep Latent Variable Model based Vertical Federated Learning with Flexible Alignment and Labeling Scenarios
19. ICLR 2026Deep-ICE: The first globally optimal algorithm for empirical risk minimization of two-layer maxout and ReLU networks
20. ICLR 2026Dimension-Free Minimax Rates for Learning Pairwise Interactions in Attention-Style Models
21. ICLR 2026DirMoE: Dirichlet-Routed Mixture of Experts
22. ICLR 2026Exploring the Design Space of Transition Matching
23. ICLR 2026Function Induction and Task Generalization: An Interpretability Study with Off-by-One Addition
24. ICLR 2026GmNet: Revisiting Gating Mechanisms From A Frequency View
25. ICLR 2026GoR: A Unified and Extensible Generative Framework for Ordinal Regression
26. ICLR 2026HiFo-Prompt: Prompting with Hindsight and Foresight for LLM-based Automatic Heuristic Design
27. ICLR 2026Householder-Diagonalized Linear Attention (HDLA): Utilizing Enhanced Decay Mechanism for Efficient Sequence Modeling
28. ICLR 2026How Muon’s Spectral Design Benefits Generalization: A Study on Imbalanced Data
29. ICLR 2026How Transformers Learn Causal Structures In-Context: Explainable Mechanism Meets Theoretical Guarantee
30. ICLR 2026Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization
31. ICLR 2026Incentives in Federated Learning with Heterogeneous Agents
32. ICLR 2026Inference-Time Scaling of Discrete Diffusion Models via Importance Weighting and Optimal Proposal Design
33. ICLR 2026Learning AND–OR Templates for Compositional Representation in Art and Design
34. ICLR 2026Learning Self-Critiquing Mechanisms for Region-Guided Chest X-Ray Report Generation
35. ICLR 2026Leveraging Discrete Function Decomposability for Scientific Design
36. ICLR 2026Lipschitz Bandits with Stochastic Delayed Feedback
37. ICLR 2026LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft Thinking
38. ICLR 2026Local Linear Attention: An Optimal Interpolation of Linear and Softmax Attention For Test-Time Regression
39. ICLR 2026MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching Inference
40. ICLR 2026Mechanism of Task-oriented Information Removal in In-context Learning
41. ICLR 2026Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context
42. ICLR 2026Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies
43. ICLR 2026Multi-state Protein Design with DynamicMPNN
44. ICLR 2026New Hybrid Fine-Tuning Paradigm for LLMs: Algorithm Design and Convergence Analysis Framework
45. ICLR 2026Nonparametric Teaching of Attention Learners
46. ICLR 2026On the Design of One-step Diffusion via Shortcutting Flow Paths
47. ICLR 2026On the Mechanisms of Collaborative Learning in VAE Recommenders
48. ICLR 2026OSIRIS: Bridging Analog Circuit Design and Machine Learning with Scalable Dataset Generation
49. ICLR 2026Revisiting Nonstationary Kernel Design for Multi-Output Gaussian Processes
50. ICLR 2026Riemannian Variational Flow Matching for Material and Protein Design

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。