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 52 篇，第 1 / 2 页

1. ICML 2023$\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
2. ICML 2023A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imaging
3. ICML 2023A Framework for Adapting Offline Algorithms to Solve Combinatorial Multi-Armed Bandit Problems with Bandit Feedback
4. ICML 2023Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations
5. ICML 2023Bootstrapped Representations in Reinforcement Learning
6. ICML 2023Cluster-Specific Predictions with Multi-Task Gaussian Processes
7. ICML 2023Comparison of meta-learners for estimating multi-valued treatment heterogeneous effects
8. ICML 2023Competing for Shareable Arms in Multi-Player Multi-Armed Bandits
9. ICML 2023Constrained Decision Transformer for Offline Safe Reinforcement Learning
10. ICML 2023Continual Task Allocation in Meta-Policy Network via Sparse Prompting
11. ICML 2023Disentangled Multi-Fidelity Deep Bayesian Active Learning
12. ICML 2023Efficient Learning of Mesh-Based Physical Simulation with Bi-Stride Multi-Scale Graph Neural Network
13. ICML 2023Estimating Causal Effects using a Multi-task Deep Ensemble
14. ICML 2023Everyone's Preference Changes Differently: A Weighted Multi-Interest Model For Retrieval
15. ICML 2023FedAvg Converges to Zero Training Loss Linearly for Overparameterized Multi-Layer Neural Networks
16. ICML 2023Improved Active Multi-Task Representation Learning via Lasso
17. ICML 2023Information-Theoretic State Space Model for Multi-View Reinforcement Learning
18. ICML 2023K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs
19. ICML 2023Learning Intuitive Policies Using Action Features
20. ICML 2023Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation
21. ICML 2023Learning Representations without Compositional Assumptions
22. ICML 2023Less is More: Task-aware Layer-wise Distillation for Language Model Compression
23. ICML 2023MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior
24. ICML 2023Modality-Agnostic Variational Compression of Implicit Neural Representations
25. ICML 2023Multi-Layer Neural Networks as Trainable Ladders of Hilbert Spaces
26. ICML 2023Multi-Objective GFlowNets
27. ICML 2023Multi-Task Differential Privacy Under Distribution Skew
28. ICML 2023Multi-task Hierarchical Adversarial Inverse Reinforcement Learning
29. ICML 2023Multi-Task Off-Policy Learning from Bandit Feedback
30. ICML 2023Multi-task Representation Learning for Pure Exploration in Linear Bandits
31. ICML 2023Multi-Task Structural Learning using Local Task Similarity induced Neuron Creation and Removal
32. ICML 2023Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally Coupled Oscillatory Recurrent Neural Networks
33. ICML 2023On Uni-Modal Feature Learning in Supervised Multi-Modal Learning
34. ICML 2023PAC Generalization via Invariant Representations
35. ICML 2023Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models
36. ICML 2023Pareto Regret Analyses in Multi-objective Multi-armed Bandit
37. ICML 2023Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information Sharing
38. ICML 2023PCA-based Multi-Task Learning: a Random Matrix Approach
39. ICML 2023Provable Multi-instance Deep AUC Maximization with Stochastic Pooling
40. ICML 2023Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup
41. ICML 2023Recasting Self-Attention with Holographic Reduced Representations
42. ICML 2023Recovering Top-Two Answers and Confusion Probability in Multi-Choice Crowdsourcing
43. ICML 2023Revisiting Pseudo-Label for Single-Positive Multi-Label Learning
44. ICML 2023Robust Subtask Learning for Compositional Generalization
45. ICML 2023Statistical Inference on Multi-armed Bandits with Delayed Feedback
46. ICML 2023Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning
47. ICML 2023Task-Specific Skill Localization in Fine-tuned Language Models
48. ICML 2023Tensor Gaussian Process with Contraction for Multi-Channel Imaging Analysis
49. ICML 2023Tight Regret Bounds for Single-pass Streaming Multi-armed Bandits
50. ICML 2023Towards Understanding Generalization of Macro-AUC in Multi-label Learning

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。