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 5 / 8 页

  1. NeurIPS 2025PROFIT: A Specialized Optimizer for Deep Fine Tuning
  2. NeurIPS 2025Prompt Tuning Decision Transformers with Structured and Scalable Bandits
  3. NeurIPS 2025Provably Efficient Multi-Task Meta Bandit Learning via Shared Representations
  4. NeurIPS 2025Quantifying Task-relevant Similarities in Representations Using Decision Variable Correlations
  5. NeurIPS 2025RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts
  6. NeurIPS 2025RAM-W600: A Multi-Task Wrist Dataset and Benchmark for Rheumatoid Arthritis
  7. NeurIPS 2025ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model
  8. NeurIPS 2025RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models
  9. NeurIPS 2025RNNs perform task computations by dynamically warping neural representations
  10. NeurIPS 2025RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness
  11. NeurIPS 2025SAINT: Sequence-Aware Integration for Spatial Transcriptomics Multi-View Clustering
  12. NeurIPS 2025Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs
  13. NeurIPS 2025Scalable Cross-View Sample Alignment for Multi-View Clustering with View Structure Similarity
  14. NeurIPS 2025Scaling Image Geo-Localization to Continent Level
  15. NeurIPS 2025SIFusion: A Unified Fusion Framework for Multi-granularity Arctic Sea Ice Forecasting
  16. NeurIPS 2025Single GPU Task Adaptation of Pathology Foundation Models for Whole Slide Image Analysis
  17. NeurIPS 2025SMARTraj$^2$: A Stable Multi-City Adaptive Method for Multi-View Spatio-Temporal Trajectory Representation Learning
  18. NeurIPS 2025Soft Task-Aware Routing of Experts for Equivariant Representation Learning
  19. NeurIPS 2025SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D Tracking
  20. NeurIPS 2025Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain
  21. NeurIPS 2025Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations
  22. NeurIPS 2025Theory-Driven Label-Specific Representation for Incomplete Multi-View Multi-Label Learning
  23. NeurIPS 2025Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration
  24. NeurIPS 2025TS-MOF: Two-Stage Multi-Objective Fine-tuning for Long-Tailed Recognition
  25. NeurIPS 2025Unbiased Prototype Consistency Learning for Multi-Modal and Multi-Task Object Re-Identification
  26. NeurIPS 2025VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models
  27. NeurIPS 2025Where Graph Meets Heterogeneity: Multi-View Collaborative Graph Experts
  28. NeurIPS 2024$C^2M^3$: Cycle-Consistent Multi-Model Merging
  29. NeurIPS 2024$SE(3)$ Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation
  30. NeurIPS 2024A New Neural Kernel Regime: The Inductive Bias of Multi-Task Learning
  31. NeurIPS 2024A Swiss Army Knife for Heterogeneous Federated Learning: Flexible Coupling via Trace Norm
  32. NeurIPS 2024Adversarially Robust Multi-task Representation Learning
  33. NeurIPS 2024AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers
  34. NeurIPS 2024Autonomous Agents for Collaborative Task under Information Asymmetry
  35. NeurIPS 2024BAKU: An Efficient Transformer for Multi-Task Policy Learning
  36. NeurIPS 2024Beyond task diversity: provable representation transfer for sequential multitask linear bandits
  37. NeurIPS 2024CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding
  38. NeurIPS 2024CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions
  39. NeurIPS 2024Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning
  40. NeurIPS 2024DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning
  41. NeurIPS 2024Efficiency for Free: Ideal Data Are Transportable Representations
  42. NeurIPS 2024Efficient Multi-task LLM Quantization and Serving for Multiple LoRA Adapters
  43. NeurIPS 2024Efficient Multi-task Reinforcement Learning with Cross-Task Policy Guidance
  44. NeurIPS 2024EMR-Merging: Tuning-Free High-Performance Model Merging
  45. NeurIPS 2024Evaluate then Cooperate: Shapley-based View Cooperation Enhancement for Multi-view Clustering
  46. NeurIPS 2024Exploring the Precise Dynamics of Single-Layer GAN Models: Leveraging Multi-Feature Discriminators for High-Dimensional Subspace Learning
  47. NeurIPS 2024Extending Multi-modal Contrastive Representations
  48. NeurIPS 2024Flexible task abstractions emerge in linear networks with fast and bounded units
  49. NeurIPS 2024GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidance
  50. NeurIPS 2024Generative Retrieval Meets Multi-Graded Relevance

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