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 1,181 篇，第 17 / 24 页
- ICML 2024MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistance
- ICML 2024Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models
- ICML 2024Multi-Fidelity Residual Neural Processes for Scalable Surrogate Modeling
- ICML 2024Multi-group Learning for Hierarchical Groups
- ICML 2024Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning
- ICML 2024Multi-Patch Prediction: Adapting Language Models for Time Series Representation Learning
- ICML 2024Multi-Source Conformal Inference Under Distribution Shift
- ICML 2024Multi-View Clustering by Inter-cluster Connectivity Guided Reward
- ICML 2024Multi-View Stochastic Block Models
- ICML 2024MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts
- ICML 2024Neural Collapse in Multi-label Learning with Pick-all-label Loss
- ICML 2024Nonparametric Teaching of Implicit Neural Representations
- ICML 2024On Multi-Armed Bandit with Impatient Arms
- ICML 2024On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm
- ICML 2024On the Origins of Linear Representations in Large Language Models
- ICML 2024One for All: A Universal Generator for Concept Unlearnability via Multi-Modal Alignment
- ICML 2024Out-of-Distribution Detection via Deep Multi-Comprehension Ensemble
- ICML 2024Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks
- ICML 2024Rapid Learning without Catastrophic Forgetting in the Morris Water Maze
- ICML 2024Regression with Multi-Expert Deferral
- ICML 2024Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation
- ICML 2024Representation Surgery for Multi-Task Model Merging
- ICML 2024Robust Multi-Task Learning with Excess Risks
- ICML 2024SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals
- ICML 2024Sparse-to-dense Multimodal Image Registration via Multi-Task Learning
- ICML 2024StrWAEs to Invariant Representations
- ICML 2024Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments
- ICML 2024Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models
- ICML 2024Task-aware Orthogonal Sparse Network for Exploring Shared Knowledge in Continual Learning
- ICML 2024TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge
- ICML 2024Training Greedy Policy for Proposal Batch Selection in Expensive Multi-Objective Combinatorial Optimization
- ICML 2024Unbiased Multi-Label Learning from Crowdsourced Annotations
- NeurIPS 2024$C^2M^3$: Cycle-Consistent Multi-Model Merging
- NeurIPS 2024$SE(3)$ Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation
- NeurIPS 2024A New Neural Kernel Regime: The Inductive Bias of Multi-Task Learning
- NeurIPS 2024A Swiss Army Knife for Heterogeneous Federated Learning: Flexible Coupling via Trace Norm
- NeurIPS 2024Adversarially Robust Multi-task Representation Learning
- NeurIPS 2024AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers
- NeurIPS 2024Autonomous Agents for Collaborative Task under Information Asymmetry
- NeurIPS 2024BAKU: An Efficient Transformer for Multi-Task Policy Learning
- NeurIPS 2024Beyond task diversity: provable representation transfer for sequential multitask linear bandits
- NeurIPS 2024CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding
- NeurIPS 2024CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions
- NeurIPS 2024Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning
- NeurIPS 2024DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning
- NeurIPS 2024Efficiency for Free: Ideal Data Are Transportable Representations
- NeurIPS 2024Efficient Multi-task LLM Quantization and Serving for Multiple LoRA Adapters
- NeurIPS 2024Efficient Multi-task Reinforcement Learning with Cross-Task Policy Guidance
- NeurIPS 2024EMR-Merging: Tuning-Free High-Performance Model Merging
- NeurIPS 2024Evaluate then Cooperate: Shapley-based View Cooperation Enhancement for Multi-view Clustering
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。