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 227 篇，第 3 / 5 页

101. ICLR 2024MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo
102. ICLR 2024Object-Centric Learning with Slot Mixture Module
103. ICLR 2024Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE
104. ICLR 2024Parameter-Efficient Multi-Task Model Fusion with Partial Linearization
105. ICLR 2024Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes
106. ICLR 2024Robot Fleet Learning via Policy Merging
107. ICLR 2024Task structure and nonlinearity jointly determine learned representational geometry
108. ICLR 2024Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets
109. ICML 2024A Hierarchical Adaptive Multi-Task Reinforcement Learning Framework for Multiplier Circuit Design
110. ICML 2024A Probabilistic Approach to Learning the Degree of Equivariance in Steerable CNNs
111. ICML 2024Applying language models to algebraic topology: generating simplicial cycles using multi-labeling in Wu's formula
112. ICML 2024Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning
113. ICML 2024Better & Faster Large Language Models via Multi-token Prediction
114. ICML 2024Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domains
115. ICML 2024Calibration Bottleneck: Over-compressed Representations are Less Calibratable
116. ICML 2024Contrasting Multiple Representations with the Multi-Marginal Matching Gap
117. ICML 2024DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning
118. ICML 2024Decouple then Classify: A Dynamic Multi-view Labeling Strategy with Shared and Specific Information
119. ICML 2024DMTG: One-Shot Differentiable Multi-Task Grouping
120. ICML 2024Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems
121. ICML 2024Fair Resource Allocation in Multi-Task Learning
122. ICML 2024Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits
123. ICML 2024GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks
124. ICML 2024Hard Tasks First: Multi-Task Reinforcement Learning Through Task Scheduling
125. ICML 2024HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning
126. ICML 2024Hybrid Neural Representations for Spherical Data
127. ICML 2024Implicit Representations via Operator Learning
128. ICML 2024Improving Transformers with Dynamically Composable Multi-Head Attention
129. ICML 2024Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks
130. ICML 2024Learning Useful Representations of Recurrent Neural Network Weight Matrices
131. ICML 2024Mapping the Multiverse of Latent Representations
132. ICML 2024Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning
133. ICML 2024Merging Multi-Task Models via Weight-Ensembling Mixture of Experts
134. ICML 2024MF-CLR: Multi-Frequency Contrastive Learning Representation for Time Series
135. ICML 2024MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistance
136. ICML 2024Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models
137. ICML 2024Multi-Fidelity Residual Neural Processes for Scalable Surrogate Modeling
138. ICML 2024Multi-group Learning for Hierarchical Groups
139. ICML 2024Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning
140. ICML 2024Multi-Patch Prediction: Adapting Language Models for Time Series Representation Learning
141. ICML 2024Multi-Source Conformal Inference Under Distribution Shift
142. ICML 2024Multi-View Clustering by Inter-cluster Connectivity Guided Reward
143. ICML 2024Multi-View Stochastic Block Models
144. ICML 2024MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts
145. ICML 2024Neural Collapse in Multi-label Learning with Pick-all-label Loss
146. ICML 2024Nonparametric Teaching of Implicit Neural Representations
147. ICML 2024On Multi-Armed Bandit with Impatient Arms
148. ICML 2024On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm
149. ICML 2024On the Origins of Linear Representations in Large Language Models
150. ICML 2024One for All: A Universal Generator for Concept Unlearnability via Multi-Modal Alignment

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。