多任务学习论文趋势 2023–2026
共享表示
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,181 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 111 | 43 | 52 | 82 | 288 |
| 2024 | 61 | 31 | 58 | 77 | 227 |
| 2025 | 101 | 40 | 47 | 76 | 264 |
| 2026 | 126 | 57 | 91 | 128 | 402 |
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 171 篇，第 4 / 4 页
- ICLR 2023Multi-level Protein Structure Pre-training via Prompt Learning
- ICLR 2023Multi-objective optimization via equivariant deep hypervolume approximation
- ICLR 2023Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve
- ICLR 2023Multi-skill Mobile Manipulation for Object Rearrangement
- ICLR 2023Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization
- ICLR 2023Multimodal Federated Learning via Contrastive Representation Ensemble
- ICLR 2023Not All Tasks Are Born Equal: Understanding Zero-Shot Generalization
- ICLR 2023Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes
- ICLR 2023Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshots
- ICLR 2023Recon: Reducing Conflicting Gradients From the Root For Multi-Task Learning
- ICLR 2023Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting
- ICLR 2023Simple Emergent Action Representations from Multi-Task Policy Training
- ICLR 2023SLTUNET: A Simple Unified Model for Sign Language Translation
- ICLR 2023SMART: Self-supervised Multi-task pretrAining with contRol Transformers
- ICLR 2023Stochastic Multi-Person 3D Motion Forecasting
- ICLR 2023STREET: A MULTI-TASK STRUCTURED REASONING AND EXPLANATION BENCHMARK
- ICLR 2023Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks
- ICLR 2023Task-customized Masked Autoencoder via Mixture of Cluster-conditional Experts
- ICLR 2023TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding
- ICLR 2023Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Tasks
- ICLR 2023Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查多任务学习在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "multi-task-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。