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 288 篇，第 4 / 6 页

  1. ICML 2023Multi-Objective GFlowNets
  2. ICML 2023Multi-Task Differential Privacy Under Distribution Skew
  3. ICML 2023Multi-task Hierarchical Adversarial Inverse Reinforcement Learning
  4. ICML 2023Multi-Task Off-Policy Learning from Bandit Feedback
  5. ICML 2023Multi-task Representation Learning for Pure Exploration in Linear Bandits
  6. ICML 2023Multi-Task Structural Learning using Local Task Similarity induced Neuron Creation and Removal
  7. ICML 2023Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally Coupled Oscillatory Recurrent Neural Networks
  8. ICML 2023On Uni-Modal Feature Learning in Supervised Multi-Modal Learning
  9. ICML 2023PAC Generalization via Invariant Representations
  10. ICML 2023Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models
  11. ICML 2023Pareto Regret Analyses in Multi-objective Multi-armed Bandit
  12. ICML 2023Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information Sharing
  13. ICML 2023PCA-based Multi-Task Learning: a Random Matrix Approach
  14. ICML 2023Provable Multi-instance Deep AUC Maximization with Stochastic Pooling
  15. ICML 2023Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup
  16. ICML 2023Recasting Self-Attention with Holographic Reduced Representations
  17. ICML 2023Recovering Top-Two Answers and Confusion Probability in Multi-Choice Crowdsourcing
  18. ICML 2023Revisiting Pseudo-Label for Single-Positive Multi-Label Learning
  19. ICML 2023Robust Subtask Learning for Compositional Generalization
  20. ICML 2023Statistical Inference on Multi-armed Bandits with Delayed Feedback
  21. ICML 2023Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning
  22. ICML 2023Task-Specific Skill Localization in Fine-tuned Language Models
  23. ICML 2023Tensor Gaussian Process with Contraction for Multi-Channel Imaging Analysis
  24. ICML 2023Tight Regret Bounds for Single-pass Streaming Multi-armed Bandits
  25. ICML 2023Towards Understanding Generalization of Macro-AUC in Multi-label Learning
  26. ICML 2023Understanding the Complexity Gains of Single-Task RL with a Curriculum
  27. ICML 2023Unifying Molecular and Textual Representations via Multi-task Language Modelling
  28. NeurIPS 2023A Spectral Algorithm for List-Decodable Covariance Estimation in Relative Frobenius Norm
  29. NeurIPS 2023AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three Weeks
  30. NeurIPS 2023Achieving Cross Modal Generalization with Multimodal Unified Representation
  31. NeurIPS 2023Active Bipartite Ranking
  32. NeurIPS 2023Active representation learning for general task space with applications in robotics
  33. NeurIPS 2023Addressing Negative Transfer in Diffusion Models
  34. NeurIPS 2023Agnostic Multi-Group Active Learning
  35. NeurIPS 2023AIMS: All-Inclusive Multi-Level Segmentation for Anything
  36. NeurIPS 2023An active learning framework for multi-group mean estimation
  37. NeurIPS 2023Analysis of Variance of Multiple Causal Networks
  38. NeurIPS 2023Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent
  39. NeurIPS 2023Bandit Social Learning under Myopic Behavior
  40. NeurIPS 2023Bandit Task Assignment with Unknown Processing Time
  41. NeurIPS 2023BanditPAM++: Faster $k$-medoids Clustering
  42. NeurIPS 2023CaMP: Causal Multi-policy Planning for Interactive Navigation in Multi-room Scenes
  43. NeurIPS 2023Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer
  44. NeurIPS 2023Chatting Makes Perfect: Chat-based Image Retrieval
  45. NeurIPS 2023Class-Distribution-Aware Pseudo-Labeling for Semi-Supervised Multi-Label Learning
  46. NeurIPS 2023CMMA: Benchmarking Multi-Affection Detection in Chinese Multi-Modal Conversations
  47. NeurIPS 2023Connecting Multi-modal Contrastive Representations
  48. NeurIPS 2023Conservative Offline Policy Adaptation in Multi-Agent Games
  49. NeurIPS 2023Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning
  50. NeurIPS 2023Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning

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