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 16 / 24 页

  1. ICLR 2024Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning
  2. ICLR 2024Denoising Task Routing for Diffusion Models
  3. ICLR 2024Diffusion Models for Multi-Task Generative Modeling
  4. ICLR 2024Disentangling Time Series Representations via Contrastive Independence-of-Support on l-Variational Inference
  5. ICLR 2024DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks
  6. ICLR 2024Experimental Design for Multi-Channel Imaging via Task-Driven Feature Selection
  7. ICLR 2024From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Prediction
  8. ICLR 2024GenSim: Generating Robotic Simulation Tasks via Large Language Models
  9. ICLR 2024Hybrid Sharing for Multi-Label Image Classification
  10. ICLR 2024MAP IT to Visualize Representations
  11. ICLR 2024MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction Following
  12. ICLR 2024Multi-Scale Representations by Varying Window Attention for Semantic Segmentation
  13. ICLR 2024Multi-task Learning with 3D-Aware Regularization
  14. ICLR 2024Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts
  15. ICLR 2024Multi-View Causal Representation Learning with Partial Observability
  16. ICLR 2024Multi-View Representation is What You Need for Point-Cloud Pre-Training
  17. ICLR 2024MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo
  18. ICLR 2024Object-Centric Learning with Slot Mixture Module
  19. ICLR 2024Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE
  20. ICLR 2024Parameter-Efficient Multi-Task Model Fusion with Partial Linearization
  21. ICLR 2024Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes
  22. ICLR 2024Robot Fleet Learning via Policy Merging
  23. ICLR 2024Task structure and nonlinearity jointly determine learned representational geometry
  24. ICLR 2024Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets
  25. ICML 2024A Hierarchical Adaptive Multi-Task Reinforcement Learning Framework for Multiplier Circuit Design
  26. ICML 2024A Probabilistic Approach to Learning the Degree of Equivariance in Steerable CNNs
  27. ICML 2024Applying language models to algebraic topology: generating simplicial cycles using multi-labeling in Wu's formula
  28. ICML 2024Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning
  29. ICML 2024Better & Faster Large Language Models via Multi-token Prediction
  30. ICML 2024Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domains
  31. ICML 2024Calibration Bottleneck: Over-compressed Representations are Less Calibratable
  32. ICML 2024Contrasting Multiple Representations with the Multi-Marginal Matching Gap
  33. ICML 2024DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning
  34. ICML 2024Decouple then Classify: A Dynamic Multi-view Labeling Strategy with Shared and Specific Information
  35. ICML 2024DMTG: One-Shot Differentiable Multi-Task Grouping
  36. ICML 2024Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems
  37. ICML 2024Fair Resource Allocation in Multi-Task Learning
  38. ICML 2024Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits
  39. ICML 2024GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks
  40. ICML 2024Hard Tasks First: Multi-Task Reinforcement Learning Through Task Scheduling
  41. ICML 2024HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning
  42. ICML 2024Hybrid Neural Representations for Spherical Data
  43. ICML 2024Implicit Representations via Operator Learning
  44. ICML 2024Improving Transformers with Dynamically Composable Multi-Head Attention
  45. ICML 2024Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks
  46. ICML 2024Learning Useful Representations of Recurrent Neural Network Weight Matrices
  47. ICML 2024Mapping the Multiverse of Latent Representations
  48. ICML 2024Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning
  49. ICML 2024Merging Multi-Task Models via Weight-Ensembling Mixture of Experts
  50. ICML 2024MF-CLR: Multi-Frequency Contrastive Learning Representation for Time Series

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