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 399 篇，第 4 / 8 页

  1. NeurIPS 2025Do different prompting methods yield a common task representation in language models?
  2. NeurIPS 2025EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretraining
  3. NeurIPS 2025Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddings
  4. NeurIPS 2025Exploring Tradeoffs through Mode Connectivity for Multi-Task Learning
  5. NeurIPS 2025Extracting task-relevant preserved dynamics from contrastive aligned neural recordings
  6. NeurIPS 2025Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes
  7. NeurIPS 2025Federated Continual Learning via Orchestrating Multi-Scale Expertise
  8. NeurIPS 2025Federated Multi-armed Bandits with Efficient Bit-Level Communications
  9. NeurIPS 2025FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts
  10. NeurIPS 2025FedRAM: Federated Reweighting and Aggregation for Multi-Task Learning
  11. NeurIPS 2025Find your Needle: Small Object Image Retrieval via Multi-Object Attention Optimization
  12. NeurIPS 2025GAMMA: Gated Multi-hop Message Passing for Homophily-Agnostic Node Representation in GNNs
  13. NeurIPS 2025GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining
  14. NeurIPS 2025GreenHyperSpectra: A multi-source hyperspectral dataset for global vegetation trait prediction
  15. NeurIPS 2025Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes
  16. NeurIPS 2025HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models
  17. NeurIPS 2025HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models
  18. NeurIPS 2025Hypergraph-Enhanced Contrastive Learning for Multi-View Clustering with Hyper-Laplacian Regularization
  19. NeurIPS 2025IDOL: Meeting Diverse Distribution Shifts with Prior Physics for Tropical Cyclone Multi-Task Estimation
  20. NeurIPS 2025Learn and Ensemble Bridge Adapters for Multi-domain Task Incremental Learning
  21. NeurIPS 2025Learning from Disjoint Views: A Contrastive Prototype Matching Network for Fully Incomplete Multi-View Clustering
  22. NeurIPS 2025Learning Multi-Source and Robust Representations for Continual Learning
  23. NeurIPS 2025Learning Orthogonal Multi-Index Models: A Fine-Grained Information Exponent Analysis
  24. NeurIPS 2025Learning Shared Representations from Unpaired Data
  25. NeurIPS 2025Learning Task-Agnostic Representations through Multi-Teacher Distillation
  26. NeurIPS 2025LIFEBENCH: Evaluating Length Instruction Following in Large Language Models
  27. NeurIPS 2025MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification
  28. NeurIPS 2025Meta-World+: An Improved, Standardized, RL Benchmark
  29. NeurIPS 2025MoORE: SVD-based Model MoE-ization for Conflict- and Oblivion-Resistant Multi-Task Adaptation
  30. NeurIPS 2025MOTION: Multi-Sculpt Evolutionary Coarsening for Federated Continual Graph Learning
  31. NeurIPS 2025Multi-dataset Joint Pre-training of Emotional EEG Enables Generalizable Affective Computing
  32. NeurIPS 2025Multi-Expert Distributionally Robust Optimization for Out-of-Distribution Generalization
  33. NeurIPS 2025Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
  34. NeurIPS 2025Multi-modal contrastive learning adapts to intrinsic dimensions of shared latent variables
  35. NeurIPS 2025Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP
  36. NeurIPS 2025MultiNet: Adaptive Multi-Viewed Subgraph Convolutional Networks for Graph Classification
  37. NeurIPS 2025MVSMamba: Multi-View Stereo with State Space Model
  38. NeurIPS 2025NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective
  39. NeurIPS 2025Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations
  40. NeurIPS 2025Objective Soups: Multilingual Multi-Task Modeling for Speech Processing
  41. NeurIPS 2025Omni-Mol: Multitask Molecular Model for Any-to-any Modalities
  42. NeurIPS 2025On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding
  43. NeurIPS 2025One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learning
  44. NeurIPS 2025OPTFM: A Scalable Multi-View Graph Transformer for Hierarchical Pre-Training in Combinatorial Optimization
  45. NeurIPS 2025Optimal Estimation of the Best Mean in Multi-Armed Bandits
  46. NeurIPS 2025Optimal Spectral Transitions in High-Dimensional Multi-Index Models
  47. NeurIPS 2025PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts
  48. NeurIPS 2025Place Cells as Multi-Scale Position Embeddings: Random Walk Transition Kernels for Path Planning
  49. NeurIPS 2025pLSTM: parallelizable Linear Source Transition Mark networks
  50. NeurIPS 2025Preserving Task-Relevant Information Under Linear Concept Removal

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