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

每年论文数

各会议论文数

按年份和会议统计

多任务学习论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023111435282288
202461315877227
2025101404776264
20261265791128402

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

全部多任务学习论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 248 篇，第 4 / 5 页

  1. ICML 2024Fair Resource Allocation in Multi-Task Learning
  2. ICML 2024Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits
  3. ICML 2024GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks
  4. ICML 2024Hard Tasks First: Multi-Task Reinforcement Learning Through Task Scheduling
  5. ICML 2024HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning
  6. ICML 2024Hybrid Neural Representations for Spherical Data
  7. ICML 2024Implicit Representations via Operator Learning
  8. ICML 2024Improving Transformers with Dynamically Composable Multi-Head Attention
  9. ICML 2024Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks
  10. ICML 2024Learning Useful Representations of Recurrent Neural Network Weight Matrices
  11. ICML 2024Mapping the Multiverse of Latent Representations
  12. ICML 2024Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning
  13. ICML 2024Merging Multi-Task Models via Weight-Ensembling Mixture of Experts
  14. ICML 2024MF-CLR: Multi-Frequency Contrastive Learning Representation for Time Series
  15. ICML 2024MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistance
  16. ICML 2024Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models
  17. ICML 2024Multi-Fidelity Residual Neural Processes for Scalable Surrogate Modeling
  18. ICML 2024Multi-group Learning for Hierarchical Groups
  19. ICML 2024Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning
  20. ICML 2024Multi-Patch Prediction: Adapting Language Models for Time Series Representation Learning
  21. ICML 2024Multi-Source Conformal Inference Under Distribution Shift
  22. ICML 2024Multi-View Clustering by Inter-cluster Connectivity Guided Reward
  23. ICML 2024Multi-View Stochastic Block Models
  24. ICML 2024MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts
  25. ICML 2024Neural Collapse in Multi-label Learning with Pick-all-label Loss
  26. ICML 2024Nonparametric Teaching of Implicit Neural Representations
  27. ICML 2024On Multi-Armed Bandit with Impatient Arms
  28. ICML 2024On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm
  29. ICML 2024On the Origins of Linear Representations in Large Language Models
  30. ICML 2024One for All: A Universal Generator for Concept Unlearnability via Multi-Modal Alignment
  31. ICML 2024Out-of-Distribution Detection via Deep Multi-Comprehension Ensemble
  32. ICML 2024Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks
  33. ICML 2024Rapid Learning without Catastrophic Forgetting in the Morris Water Maze
  34. ICML 2024Regression with Multi-Expert Deferral
  35. ICML 2024Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation
  36. ICML 2024Representation Surgery for Multi-Task Model Merging
  37. ICML 2024Robust Multi-Task Learning with Excess Risks
  38. ICML 2024SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals
  39. ICML 2024Sparse-to-dense Multimodal Image Registration via Multi-Task Learning
  40. ICML 2024StrWAEs to Invariant Representations
  41. ICML 2024Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments
  42. ICML 2024Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models
  43. ICML 2024Task-aware Orthogonal Sparse Network for Exploring Shared Knowledge in Continual Learning
  44. ICML 2024TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge
  45. ICML 2024Training Greedy Policy for Proposal Batch Selection in Expensive Multi-Objective Combinatorial Optimization
  46. ICML 2024Unbiased Multi-Label Learning from Crowdsourced Annotations
  47. ICML 2023$\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
  48. ICML 2023A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imaging
  49. ICML 2023A Framework for Adapting Offline Algorithms to Solve Combinatorial Multi-Armed Bandit Problems with Bandit Feedback
  50. ICML 2023Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations

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"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「元学习与迁移」下的其他主题