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 107 篇，第 1 / 3 页

1. ICML 2026A Consensus Anchor-guided Hypergraph Framework for Incomplete Multi-view Clustering
2. ICML 2026A Systematic Study of Behavioral Cloning for Scientific Data Annotation
3. ICML 2026A Tale of Two Problems: Multi-Task Bilevel Learning Meets Equality Constrained Multi-Objective Optimization
4. ICML 2026Accelerated Multiple Wasserstein Gradient Flows for Multi-objective Distributional Optimization
5. ICML 2026Adaptive Personalized Federated Learning via Multi-task Averaging of Kernel Mean Embeddings
6. ICML 2026AES: Curing Optimizer Blindness in Long-Tailed Recognition via State-Aware Correction
7. ICML 2026Alleviating Observation Bias via Causal-Invariant Meta-Learning for Unbalanced Incomplete Multi-view Clustering
8. ICML 2026AMDP: Asynchronous Multi-Directional Pipeline Parallelism for Large-Scale Models Training
9. ICML 2026Beyond Independence: Learning Correlated Views for Variational Incomplete Multi-View Clustering
10. ICML 2026Beyond Model Ranking: Predictability-Aligned Evaluation for Time Series Forecasting
11. ICML 2026Breaking Multi-Task Curse: Reward-Weighted Evolution for Black-Box Many-Task Optimization
12. ICML 2026Calibrated Preference Learning: The Case of Label Ranking
13. ICML 2026Calibrating Decision Robustness via Inverse Conformal Risk Control
14. ICML 2026Constrained Multi-Objective Reinforcement Learning with Max-Min Criterion
15. ICML 2026Contractive Anchor Resolvent Diffusion for Incomplete Multi-View Clustering
16. ICML 2026Convergence Rate of the Last Iterate of Stochastic Proximal Algorithms
17. ICML 2026CORE-MTL: Rethinking Gradient Balancing via Causal Orthogonal Representations
18. ICML 2026Cross-task Calibration for Asynchronous Federated Continual Learning
19. ICML 2026CrossQ: Task-Aligned Cross-Token Conditional Quantization for Late Interaction Retrieval
20. ICML 2026Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
21. ICML 2026Discretely-Refined Multi-view Clustering via Aligned Anchor Learning
22. ICML 2026DITRON: Distributed Multi-level Tiling Compiler for Parallel Tensor Programs
23. ICML 2026Diversity-Driven Offline Multi-Objective Optimization via Nested Pareto Set Learning
24. ICML 2026Divide and Learn: Multi-Objective Combinatorial Optimization at Scale
25. ICML 2026DREAM: A Unified Framework for Drift-Corrected Federated Multi-Objective Learning
26. ICML 2026Dual-Calibration Multi-View Clustering via Compact Anchor Learning
27. ICML 2026Dual-stage Contrastive Learning-enhanced Multi-view Variational Clustering
28. ICML 2026Efficient Multi-round LLM Inference over Disaggregated Serving
29. ICML 2026Enhanced Multi-Instance Partial Label Learning via Average Gradient Outer Product
30. ICML 2026Exploration-free Algorithms for Multi-group Mean Estimation
31. ICML 2026Exploring 3D Dataset Pruning
32. ICML 2026FACT: Fuzzy Alignment with Comorbidity Topology for Reliable Multi-Label Medical Image Diagnosis
33. ICML 2026Federated Multi-view Clustering for Remote Sensing Data
34. ICML 2026Feedback Control for Multi-Objective Graph Self-Supervision
35. ICML 2026FIRE: Multi-Fidelity Regression with Distribution-Conditioned In-Context Learning Using Tabular Foundation Models
36. ICML 2026Flexible Kernels for Protein Property Prediction
37. ICML 2026From Interaction Trajectories to Prompt Rules: Credit Assignment for Multi-Agent Prompt Optimization
38. ICML 2026GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation
39. ICML 2026Goal-Conditioned Agents that Learn Everything All at Once
40. ICML 2026GRAPE: Let GRPO Supervise Query Rewriting by Ranking for Retrieval
41. ICML 2026Hierarchical Anchor Graph Learning for Multi-View Clustering
42. ICML 2026How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning
43. ICML 2026Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning
44. ICML 2026HyMTRL: A Hybrid Multi-Task Reinforcement Learning Framework via Phased Policy Evolution
45. ICML 2026Identifying dependent components from multi-domain linear mixtures
46. ICML 2026Is Task-Specific Training Necessary for Anomaly Detection?
47. ICML 2026Iterated Population Based Training with Task-Agnostic Restarts
48. ICML 2026Knothe-Rosenblatt Quantile Regression for Risk-sensitive Multi-objective Reinforcement Learning
49. ICML 2026Landmark-Guided Policy Optimization for Multi-Objective Language Model Selection
50. ICML 2026Layer-Centric Factors of Variation Disentanglement for Task- and Model-Agnostic Generalization

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。