多任务排序论文趋势 2023–2026

主要结论

• 多任务排序论文从 2023 年的 252 篇增长到 2026 年的 480 篇，三年间扩大到约 1.9 倍。
• NeurIPS 是发多任务排序论文最多的会议，2023–2026 年共 485 篇，占四个会议总量的 34%。
• 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 8 篇增至 2026 年的 52 篇。
• 在「推荐与广告」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的点击率预测是 2.6 倍，多任务排序是 1.9 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 Mahalanobis Margin \texorpdfstring{$\gamma_{\min}$}{gamma\_min} Bound on Task Confusion in Pretrained Class-Incremental Learning: From Infeasibility to Exponential Attenuation
• ICML 2026Adaptive Personalized Federated Learning via Multi-task Averaging of Kernel Mean Embeddings
• ICLR 2026Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?
• CVPR 2026A Supervised Multi-task Framework for Joint cryo-ET Restoration Enabled by
• NeurIPS 2025A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning
• ICML 2025ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning
• ICLR 2025Balanced Ranking with Relative Centrality: A multi-core periphery perspective
• CVPR 2025ACAttack: Adaptive Cross Attacking RGB-T Tracker via Multi-Modal Response Decoupling
• NeurIPS 2024CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding
• ICML 2024Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning
• ICLR 2024Order-Preserving GFlowNets
• CVPR 2024Domain Separation Graph Neural Networks for Saliency Object Ranking
• NeurIPS 2023AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three Weeks
• ICML 2023Hypervolume Knowledge Gradient: A Lookahead Approach for Multi-Objective Bayesian Optimization with Partial Information
• ICLR 2023An Extensible Multi-modal Multi-task Object Dataset with Materials
• CVPR 2023AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation
• NeurIPS 2026A Scalable Multi-Task Model for Virtual Sensors
• ICML 2026Alleviating Observation Bias via Causal-Invariant Meta-Learning for Unbalanced Incomplete Multi-view Clustering
• ICLR 2026Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature
• CVPR 2026Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers

全部多任务排序论文

共 83 篇，第 1 / 2 页

1. CVPR 2023A Light Touch Approach to Teaching Transformers Multi-View Geometry
2. CVPR 2023Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo
3. CVPR 2023AeDet: Azimuth-Invariant Multi-View 3D Object Detection
4. CVPR 2023AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation
5. CVPR 2023Batch Model Consolidation: A Multi-Task Model Consolidation Framework
6. CVPR 2023Black-Box Sparse Adversarial Attack via Multi-Objective Optimisation
7. CVPR 2023Bridging the Gap Between Model Explanations in Partially Annotated Multi-Label Classification
8. CVPR 2023CAPE: Camera View Position Embedding for Multi-View 3D Object Detection
9. CVPR 2023Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries
10. CVPR 2023CutMIB: Boosting Light Field Super-Resolution via Multi-View Image Blending
11. CVPR 2023Dealing With Cross-Task Class Discrimination in Online Continual Learning
12. CVPR 2023Decentralized Learning With Multi-Headed Distillation
13. CVPR 2023Decoupling Learning and Remembering: A Bilevel Memory Framework With Knowledge Projection for Task-Incremental Learning
14. CVPR 2023DF-Platter: Multi-Face Heterogeneous Deepfake Dataset
15. CVPR 2023Dynamic Neural Network for Multi-Task Learning Searching Across Diverse Network Topologies
16. CVPR 2023Egocentric Video Task Translation
17. CVPR 2023FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks
18. CVPR 2023G-MSM: Unsupervised Multi-Shape Matching With Graph-Based Affinity Priors
19. CVPR 2023Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process
20. CVPR 2023GeoMVSNet: Learning Multi-View Stereo With Geometry Perception
21. CVPR 2023GKEAL: Gaussian Kernel Embedded Analytic Learning for Few-Shot Class Incremental Task
22. CVPR 2023GLeaD: Improving GANs With a Generator-Leading Task
23. CVPR 2023GM-NeRF: Learning Generalizable Model-Based Neural Radiance Fields From Multi-View Images
24. CVPR 2023Hierarchical Prompt Learning for Multi-Task Learning
25. CVPR 2023Independent Component Alignment for Multi-Task Learning
26. CVPR 2023Indescribable Multi-Modal Spatial Evaluator
27. CVPR 2023Ingredient-Oriented Multi-Degradation Learning for Image Restoration
28. CVPR 2023Instant Multi-View Head Capture Through Learnable Registration
29. CVPR 2023Interventional Bag Multi-Instance Learning on Whole-Slide Pathological Images
30. CVPR 2023Language Adaptive Weight Generation for Multi-Task Visual Grounding
31. CVPR 2023MAIR: Multi-View Attention Inverse Rendering With 3D Spatially-Varying Lighting Estimation
32. CVPR 2023MaPLe: Multi-Modal Prompt Learning
33. CVPR 2023Masked Image Modeling With Local Multi-Scale Reconstruction
34. CVPR 2023MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos
35. CVPR 2023MDL-NAS: A Joint Multi-Domain Learning Framework for Vision Transformer
36. CVPR 2023MetaViewer: Towards a Unified Multi-View Representation
37. CVPR 2023MISC210K: A Large-Scale Dataset for Multi-Instance Semantic Correspondence
38. CVPR 2023Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing With Non-Learnable Primitives
39. CVPR 2023Mod-Squad: Designing Mixtures of Experts As Modular Multi-Task Learners
40. CVPR 2023MotionDiffuser: Controllable Multi-Agent Motion Prediction Using Diffusion
41. CVPR 2023MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors
42. CVPR 2023MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID
43. CVPR 2023Multi Domain Learning for Motion Magnification
44. CVPR 2023Multi-Centroid Task Descriptor for Dynamic Class Incremental Inference
45. CVPR 2023Multi-Label Compound Expression Recognition: C-EXPR Database & Network
46. CVPR 2023Multi-Level Logit Distillation
47. CVPR 2023Multi-Modal Representation Learning With Text-Driven Soft Masks
48. CVPR 2023Multi-Realism Image Compression With a Conditional Generator
49. CVPR 2023Multi-Space Neural Radiance Fields
50. CVPR 2023Multi-View Azimuth Stereo via Tangent Space Consistency

常见问题

2023–2026 年四大会议一共有多少篇多任务排序论文？

共 1,440 篇，按年份分别是 2023 年 252 篇、2024 年 315 篇、2025 年 393 篇、2026 年 480 篇。

NeurIPS 2026 有多少篇多任务排序论文？

NeurIPS 2026 有 175 篇多任务排序论文，上一届是 144 篇。

ICLR 2026 有多少篇多任务排序论文？

ICLR 2026 有 79 篇多任务排序论文，上一届是 75 篇。

ICML 2026 有多少篇多任务排序论文？

ICML 2026 有 107 篇多任务排序论文，上一届是 80 篇。

CVPR 2026 有多少篇多任务排序论文？

CVPR 2026 有 119 篇多任务排序论文，上一届是 94 篇。

哪个会议的多任务排序论文最多？

NeurIPS，2023–2026 年共 485 篇。