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 1,037 篇，第 1 / 21 页

1. CVPR 2026A Combination of Noise and Bilateral Filters Achieve Supralinear and
2. CVPR 2026A Temporal and Content Co-Awareness Latent Diffusion for Controllable Hand
3. CVPR 2026Composing Concepts from Images and Videos via Concept-prompt Binding
4. CVPR 2026CoWTracker Tracking by Warping instead of Correlation
5. CVPR 2026Cross-Subject EEG-to-Video Reconstruction and Beyond
6. CVPR 2026DDT Decoupled Diffusion Transformer
7. CVPR 2026Design Your Ad Personalized Advertising Image and Text Generation with
8. CVPR 2026Discover Segment and Select A Progressive Mechanism for Zero-shot Camouflaged
9. CVPR 2026Dual-level Adapter Boosting Prompt-free Curvilinear Structure Segmentation
10. CVPR 2026Elucidating the Design Space of Arbitrary-Noise-Based Diffusion Models
11. CVPR 2026EnergyAction Unimanual to Bimanual Composition with Energy-Based Models
12. CVPR 2026Evidential Deep Partial Label Learning to Quantify Disambiguation Uncertainty
13. CVPR 2026Fast SceneScript Fast and Accurate Language-Based 3D Scene Understanding via
14. CVPR 2026FEAT Fashion Editing and Try-On from Any Design
15. CVPR 2026Hi-Lo Prune Look at What Youll Lose before Pruning with
16. CVPR 2026iLRM An Iterative Large 3D Reconstruction Model
17. CVPR 2026Improved Mean Flows On the Challenges of Fastforward Generative Models
18. CVPR 2026Inferring Compositional 4D Scenes without Ever Seeing One
19. CVPR 2026JUMP-Hand Learning Joint-wise Uncertainty to Gate Mixture of View Experts
20. CVPR 2026LangField4D Learning Identity-Adaptive and Spatio-Temporal Continuous 4D Language Fields for
21. CVPR 2026LaSM Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI
22. CVPR 2026Lens Component Deletion based on Differentiable Ray Tracing
23. CVPR 2026Love Me Love My Label Rethinking the Role of Labels
24. CVPR 2026Mechanisms of Object Localization in Vision-Language Models
25. CVPR 2026MetroGS Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale
26. CVPR 2026Mirror Illusion Art
27. CVPR 2026MOFA-VTON More Fashion Possibilities with Fine-Grained Adaptations in Virtual Try-On
28. CVPR 2026Multigrain-aware Semantic Prototype Scanning and Tri-Token Prompt Learning Embraced High-Order
29. CVPR 2026NeAR Coupled Neural Asset-Renderer Stack
30. CVPR 2026OS-Fed One Snapshot Is All You Need
31. CVPR 2026Parallax to Align Them All An OmniParallax Attention Mechanism for
32. CVPR 2026PatchScene Patch-based Voxel Diffusion Model for Large-Scale Scene Completion
33. CVPR 2026PhyGaP Physically-Grounded Gaussians with Polarization Cues
34. CVPR 2026PointCNN Performant Convolution on Native Points
35. CVPR 2026Polarization State Tracing for Reflection Removal and Color-Consistent Reconstruction
36. CVPR 2026PosterIQ A Design Perspective Benchmark for Poster Understanding and Generation
37. CVPR 2026PosterReward Unlocking Accurate Evaluation for High-Quality Graphic Design Generation
38. CVPR 2026Prototype-as-Prompt Multimodal Sentiment Prototypes Endowing Large Language Models the Capability
39. CVPR 2026PSDesigner Automated Graphic Design with a Human-Like Creative Workflow
40. CVPR 2026RaUF Learning the Spatial Uncertainty Field of Radar
41. CVPR 2026ResDiT Evoking the Intrinsic Resolution Scalability in Diffusion Transformers
42. CVPR 2026Residual Primitive Fitting of 3D Shapes with SuperFrusta
43. CVPR 2026Sculpt4D Generating 4D Shapes via Sparse-Attention Diffusion Transformers
44. CVPR 2026SegMo Co-Designing Content-Aware Sparsity and Locally-Cohesive Segment Parallelism for Efficient
45. CVPR 2026SkyReels-Text Fine-Grained Font-Controllable Text Editing for Poster Design
46. CVPR 2026SoliReward Mitigating Susceptibility to Reward Hacking and Annotation Noise in
47. CVPR 2026Spe-BEVHead Rethinking the Detection Head Design for Birds-Eye-View Object Detection
48. CVPR 2026SpotEdit Selective Region Editing in Diffusion Transformers
49. CVPR 2026Stable Mean Flow Lyapunov-Inspired One-Step Flow Matching
50. CVPR 2026Stay in your Lane Role Specific Queries with Overlap Suppression

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。