多任务学习论文趋势 2023–2026

主要结论

• 多任务学习论文从 2023 年的 288 篇增长到 2026 年的 402 篇，三年间扩大到约 1.4 倍。
• NeurIPS 是发多任务学习论文最多的会议，2023–2026 年共 399 篇，占四个会议总量的 34%。
• 交叉方向里涨得最快的是数据集与基准：同时属于两个主题的论文从 2023 年的 6 篇增至 2026 年的 16 篇。
• 在「元学习与迁移」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的基础模型适配是 3.8 倍，多任务学习是 1.4 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 2026A Systematic Study of Behavioral Cloning for Scientific Data Annotation
• ICLR 2026Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?
• CVPR 20263D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding
• 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 2025CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs
• 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 2024Class Incremental Learning via Likelihood Ratio Based Task Prediction
• CVPR 2024Differentiable Information Bottleneck for Deterministic Multi-view Clustering
• NeurIPS 2023A Spectral Algorithm for List-Decodable Covariance Estimation in Relative Frobenius Norm
• ICML 2023A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imaging
• 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 2026Beyond Hearing: Learning Task-agnostic ExG Representations from Earphones via Physiology-informed Tokenization
• CVPR 2026Any Resolution Any Geometry From Multi-View To Multi-Patch

全部多任务学习论文

共 47 篇，第 1 / 1 页

1. ICML 2025A General Representation-Based Approach to Multi-Source Domain Adaptation
2. ICML 2025A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
3. ICML 2025A Mixed-Curvature based Pre-training Paradigm for Multi-Task Vehicle Routing Solver
4. ICML 2025A Multi-Region Brain Model to Elucidate the Role of Hippocampus in Spatially Embedded Decision-Making
5. ICML 2025A Two-Stage Learning-to-Defer Approach for Multi-Task Learning
6. ICML 2025Active Fine-Tuning of Multi-Task Policies
7. ICML 2025Algorithm Development in Neural Networks: Insights from the Streaming Parity Task
8. ICML 2025ARS: Adaptive Reward Scaling for Multi-Task Reinforcement Learning
9. ICML 2025ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning
10. ICML 2025Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning
11. ICML 2025Bifurcate then Alienate: Incomplete Multi-view Clustering via Coupled Distribution Learning with Linear Overhead
12. ICML 2025CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention
13. ICML 2025CALM: Consensus-Aware Localized Merging for Multi-Task Learning
14. ICML 2025CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging
15. ICML 2025Deep Fuzzy Multi-view Learning for Reliable Classification
16. ICML 2025Drug-TTA: Test-Time Adaptation for Drug Virtual Screening via Multi-task Meta-Auxiliary Learning
17. ICML 2025Efficient Federated Incomplete Multi-View Clustering
18. ICML 2025Fast Incomplete Multi-view Clustering by Flexible Anchor Learning
19. ICML 2025FEAT-KD: Learning Concise Representations for Single and Multi-Target Regression via TabNet Knowledge Distillation
20. ICML 2025Federated Incomplete Multi-view Clustering with Globally Fused Graph Guidance
21. ICML 2025FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making
22. ICML 2025From Spectrum-free towards Baseline-view-free: Double-track Proximity Driven Multi-view Clustering
23. ICML 2025From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining
24. ICML 2025Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning
25. ICML 2025Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens
26. ICML 2025Learngene Tells You How to Customize: Task-Aware Parameter Initialization at Flexible Scales
27. ICML 2025Learning Compact Semantic Information for Incomplete Multi-View Missing Multi-Label Classification
28. ICML 2025Learning Fused State Representations for Control from Multi-View Observations
29. ICML 2025Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation
30. ICML 2025Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
31. ICML 2025MTL-UE: Learning to Learn Nothing for Multi-Task Learning
32. ICML 2025Multi-Session Budget Optimization for Forward Auction-based Federated Learning
33. ICML 2025Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning
34. ICML 2025On the Adversarial Robustness of Multi-Kernel Clustering
35. ICML 2025Optimizing Temperature for Language Models with Multi-Sample Inference
36. ICML 2025Private Model Personalization Revisited
37. ICML 2025PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering
38. ICML 2025Provable In-Context Vector Arithmetic via Retrieving Task Concepts
39. ICML 2025Robust Consensus Anchor Learning for Efficient Multi-view Subspace Clustering
40. ICML 2025SHIELD: Multi-task Multi-distribution Vehicle Routing Solver with Sparsity and Hierarchy
41. ICML 2025SToFM: a Multi-scale Foundation Model for Spatial Transcriptomics
42. ICML 2025Task-Gated Multi-Expert Collaboration Network for Degraded Multi-Modal Image Fusion
43. ICML 2025Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods
44. ICML 2025Update Your Transformer to the Latest Release: Re-Basin of Task Vectors
45. ICML 2025Vision-Language Models Create Cross-Modal Task Representations
46. ICML 2025When can in-context learning generalize out of task distribution?
47. ICML 2025Whoever Started the interference Should End It: Guiding Data-Free Model Merging via Task Vectors

常见问题

2023–2026 年四大会议一共有多少篇多任务学习论文？

共 1,181 篇，按年份分别是 2023 年 288 篇、2024 年 227 篇、2025 年 264 篇、2026 年 402 篇。

NeurIPS 2026 有多少篇多任务学习论文？

NeurIPS 2026 有 126 篇多任务学习论文，上一届是 101 篇。

ICLR 2026 有多少篇多任务学习论文？

ICLR 2026 有 57 篇多任务学习论文，上一届是 40 篇。

ICML 2026 有多少篇多任务学习论文？

ICML 2026 有 91 篇多任务学习论文，上一届是 47 篇。

CVPR 2026 有多少篇多任务学习论文？

CVPR 2026 有 128 篇多任务学习论文，上一届是 76 篇。

哪个会议的多任务学习论文最多？

NeurIPS，2023–2026 年共 399 篇。