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 271 篇，第 1 / 6 页

1. CVPR 2025A General Adaptive Dual-level Weighting Mechanism for Remote Sensing Pansharpening
2. CVPR 2025A Selective Re-learning Mechanism for Hyperspectral Fusion Imaging
3. CVPR 2025All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages
4. CVPR 2025AniDoc: Animation Creation Made Easier
5. CVPR 2025BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices
6. CVPR 2025Breaking the Low-Rank Dilemma of Linear Attention
7. CVPR 2025CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generation
8. CVPR 2025CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images
9. CVPR 2025CASAGPT: Cuboid Arrangement and Scene Assembly for Interior Design
10. CVPR 2025Category-Agnostic Neural Object Rigging
11. CVPR 2025Classifier-Free Guidance Inside the Attraction Basin May Cause Memorization
12. CVPR 2025ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices
13. CVPR 2025Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal
14. CVPR 2025Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
15. CVPR 2025DiC: Rethinking Conv3x3 Designs in Diffusion Models
16. CVPR 2025DiffFNO: Diffusion Fourier Neural Operator
17. CVPR 2025Diffusion Model is Effectively Its Own Teacher
18. CVPR 2025EASEMVC:Efficient Dual Selection Mechanism for Deep Multi-View Clustering
19. CVPR 2025Effective Cloud Removal for Remote Sensing Images by an Improved Mean-Reverting Denoising Model with Elucidated Design Space
20. CVPR 2025EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing
21. CVPR 2025EVOS: Efficient Implicit Neural Training via EVOlutionary Selector
22. CVPR 2025Frequency-Biased Synergistic Design for Image Compression and Compensation
23. CVPR 2025From Elements to Design: A Layered Approach for Automatic Graphic Design Composition
24. CVPR 2025GO-N3RDet: Geometry Optimized NeRF-enhanced 3D Object Detector
25. CVPR 2025LineArt: A Knowledge-guided Training-free High-quality Appearance Transfer for Design Drawing with Diffusion Model
26. CVPR 2025LSNet: See Large, Focus Small
27. CVPR 2025MambaIRv2: Attentive State Space Restoration
28. CVPR 2025MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism
29. CVPR 2025NADER: Neural Architecture Design via Multi-Agent Collaboration
30. CVPR 2025OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels
31. CVPR 2025Quantization without Tears
32. CVPR 2025RC-AutoCalib: An End-to-End Radar-Camera Automatic Calibration Network
33. CVPR 2025Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation
34. CVPR 2025Rethinking Decoder Design: Improving Biomarker Segmentation Using Depth-to-Space Restoration and Residual Linear Attention
35. CVPR 2025Rethinking Spiking Self-Attention Mechanism: Implementing a-XNOR Similarity Calculation in Spiking Transformers
36. CVPR 2025Seeing A 3D World in A Grain of Sand
37. CVPR 2025SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models
38. CVPR 2025Spiking Transformer with Spatial-Temporal Attention
39. CVPR 2025Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectly
40. CVPR 2025VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction
41. ICLR 2025A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention
42. ICLR 2025AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning
43. ICLR 2025Agree to Disagree: Demystifying Homogeneous Deep Ensembles through Distributional Equivalence
44. ICLR 2025Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis
45. ICLR 2025Automated Design of Agentic Systems
46. ICLR 2025Bayesian Experimental Design Via Contrastive Diffusions
47. ICLR 2025Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks
48. ICLR 2025BodyGen: Advancing Towards Efficient Embodiment Co-Design
49. ICLR 2025Charting the Design Space of Neural Graph Representations for Subgraph Matching
50. ICLR 2025Clique Number Estimation via Differentiable Functions of Adjacency Matrix Permutations

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。