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 108 篇，第 1 / 3 页

1. NeurIPS 2025A Closer Look at Graph Transformers: Cross-Aggregation and Beyond
2. NeurIPS 2025A Cramér–von Mises Approach to Incentivizing Truthful Data Sharing
3. NeurIPS 2025A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design
4. NeurIPS 2025ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition
5. NeurIPS 2025AlphaFold Database Debiasing for Robust Inverse Folding
6. NeurIPS 2025Ambient Proteins - Training Diffusion Models on Noisy Structures
7. NeurIPS 2025Attention Mechanism, Max-Affine Partition, and Universal Approximation
8. NeurIPS 2025Attention Sinks: A 'Catch, Tag, Release' Mechanism for Embeddings
9. NeurIPS 2025Bayes optimal learning of attention-indexed models
10. NeurIPS 2025Beyond Last-Click: An Optimal Mechanism for Ad Attribution
11. NeurIPS 2025BikeBench: A Bicycle Design Benchmark for Generative Models with Objectives and Constraints
12. NeurIPS 2025Can Large Multimodal Models Understand Agricultural Scenes? Benchmarking with AgroMind
13. NeurIPS 2025Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism
14. NeurIPS 2025Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret Minimization
15. NeurIPS 2025Compress Large Language Models via Collaboration Between Learning and Matrix Approximation
16. NeurIPS 2025Convergent Functions, Divergent Forms
17. NeurIPS 2025Convolution Goes Higher-Order: A Biologically Inspired Mechanism Empowers Image Classification
18. NeurIPS 2025CPSea: Large-scale cyclic peptide-protein complex dataset for machine learning in cyclic peptide design
19. NeurIPS 2025Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RL
20. NeurIPS 2025DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer
21. NeurIPS 2025Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inference
22. NeurIPS 2025DuSA: Fast and Accurate Dual-Stage Sparse Attention Mechanism Accelerating Both Training and Inference
23. NeurIPS 2025Dynamic Masking and Auxiliary Hash Learning for Enhanced Cross-Modal Retrieval
24. NeurIPS 2025Efficient Bayesian Experiment Design with Equivariant Networks
25. NeurIPS 2025Emergence of Linear Truth Encodings in Language Models
26. NeurIPS 2025EngiBench: A Framework for Data-Driven Engineering Design Research
27. NeurIPS 2025Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism
28. NeurIPS 2025Error Forcing in Recurrent Neural Networks
29. NeurIPS 2025Exploring the Design Space of Diffusion Bridge Models
30. NeurIPS 2025Exploring the Translation Mechanism of Large Language Models
31. NeurIPS 2025Fast attention mechanisms: a tale of parallelism
32. NeurIPS 2025FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion
33. NeurIPS 2025From Self-Check to Consensus: Bayesian Strategic Decoding in Large Language Models
34. NeurIPS 2025Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
35. NeurIPS 2025Generalization Bounds for Kolmogorov-Arnold Networks (KANs) and Enhanced KANs with Lower Lipschitz Complexity
36. NeurIPS 2025Geometric Algebra-Enhanced Bayesian Flow Network for RNA Inverse Design
37. NeurIPS 2025GLID$^2$E: A Gradient-Free Lightweight Fine-tune Approach for Discrete Biological Sequence Design
38. NeurIPS 2025Hadamax Encoding: Elevating Performance in Model-Free Atari
39. NeurIPS 2025Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access
40. NeurIPS 2025How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation
41. NeurIPS 2025Impartial Selection with Predictions
42. NeurIPS 2025Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards
43. NeurIPS 2025Incentive-Aware Dynamic Resource Allocation under Long-Term Cost Constraints
44. NeurIPS 2025Incentivizing Desirable Effort Profiles in Strategic Classification: The Role of Causality and Uncertainty
45. NeurIPS 2025Incentivizing Truthful Language Models via Peer Elicitation Games
46. NeurIPS 2025Inference with correlated priors using sisters cells
47. NeurIPS 2025Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs
48. NeurIPS 2025Information-Driven Design of Imaging Systems
49. NeurIPS 2025Is Grokking a Computational Glass Relaxation?
50. NeurIPS 2025Joint Design of Protein Surface and Backbone Using a Diffusion Bridge Model

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。