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 1,181 篇，第 21 / 24 页

  1. ICLR 2023Multi-skill Mobile Manipulation for Object Rearrangement
  2. ICLR 2023Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization
  3. ICLR 2023Multimodal Federated Learning via Contrastive Representation Ensemble
  4. ICLR 2023Not All Tasks Are Born Equal: Understanding Zero-Shot Generalization
  5. ICLR 2023Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes
  6. ICLR 2023Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshots
  7. ICLR 2023Recon: Reducing Conflicting Gradients From the Root For Multi-Task Learning
  8. ICLR 2023Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting
  9. ICLR 2023Simple Emergent Action Representations from Multi-Task Policy Training
  10. ICLR 2023SLTUNET: A Simple Unified Model for Sign Language Translation
  11. ICLR 2023SMART: Self-supervised Multi-task pretrAining with contRol Transformers
  12. ICLR 2023Stochastic Multi-Person 3D Motion Forecasting
  13. ICLR 2023STREET: A MULTI-TASK STRUCTURED REASONING AND EXPLANATION BENCHMARK
  14. ICLR 2023Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks
  15. ICLR 2023Task-customized Masked Autoencoder via Mixture of Cluster-conditional Experts
  16. ICLR 2023TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding
  17. ICLR 2023Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Tasks
  18. ICLR 2023Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding
  19. ICML 2023$\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
  20. ICML 2023A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imaging
  21. ICML 2023A Framework for Adapting Offline Algorithms to Solve Combinatorial Multi-Armed Bandit Problems with Bandit Feedback
  22. ICML 2023Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations
  23. ICML 2023Bootstrapped Representations in Reinforcement Learning
  24. ICML 2023Cluster-Specific Predictions with Multi-Task Gaussian Processes
  25. ICML 2023Comparison of meta-learners for estimating multi-valued treatment heterogeneous effects
  26. ICML 2023Competing for Shareable Arms in Multi-Player Multi-Armed Bandits
  27. ICML 2023Constrained Decision Transformer for Offline Safe Reinforcement Learning
  28. ICML 2023Continual Task Allocation in Meta-Policy Network via Sparse Prompting
  29. ICML 2023Disentangled Multi-Fidelity Deep Bayesian Active Learning
  30. ICML 2023Efficient Learning of Mesh-Based Physical Simulation with Bi-Stride Multi-Scale Graph Neural Network
  31. ICML 2023Estimating Causal Effects using a Multi-task Deep Ensemble
  32. ICML 2023Everyone's Preference Changes Differently: A Weighted Multi-Interest Model For Retrieval
  33. ICML 2023FedAvg Converges to Zero Training Loss Linearly for Overparameterized Multi-Layer Neural Networks
  34. ICML 2023Improved Active Multi-Task Representation Learning via Lasso
  35. ICML 2023Information-Theoretic State Space Model for Multi-View Reinforcement Learning
  36. ICML 2023K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs
  37. ICML 2023Learning Intuitive Policies Using Action Features
  38. ICML 2023Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation
  39. ICML 2023Learning Representations without Compositional Assumptions
  40. ICML 2023Less is More: Task-aware Layer-wise Distillation for Language Model Compression
  41. ICML 2023MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior
  42. ICML 2023Modality-Agnostic Variational Compression of Implicit Neural Representations
  43. ICML 2023Multi-Layer Neural Networks as Trainable Ladders of Hilbert Spaces
  44. ICML 2023Multi-Objective GFlowNets
  45. ICML 2023Multi-Task Differential Privacy Under Distribution Skew
  46. ICML 2023Multi-task Hierarchical Adversarial Inverse Reinforcement Learning
  47. ICML 2023Multi-Task Off-Policy Learning from Bandit Feedback
  48. ICML 2023Multi-task Representation Learning for Pure Exploration in Linear Bandits
  49. ICML 2023Multi-Task Structural Learning using Local Task Similarity induced Neuron Creation and Removal
  50. ICML 2023Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally Coupled Oscillatory Recurrent Neural Networks

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