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 12 / 24 页

  1. ICML 2025Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning
  2. ICML 2025On the Adversarial Robustness of Multi-Kernel Clustering
  3. ICML 2025Optimizing Temperature for Language Models with Multi-Sample Inference
  4. ICML 2025Private Model Personalization Revisited
  5. ICML 2025PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering
  6. ICML 2025Provable In-Context Vector Arithmetic via Retrieving Task Concepts
  7. ICML 2025Robust Consensus Anchor Learning for Efficient Multi-view Subspace Clustering
  8. ICML 2025SHIELD: Multi-task Multi-distribution Vehicle Routing Solver with Sparsity and Hierarchy
  9. ICML 2025SToFM: a Multi-scale Foundation Model for Spatial Transcriptomics
  10. ICML 2025Task-Gated Multi-Expert Collaboration Network for Degraded Multi-Modal Image Fusion
  11. ICML 2025Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods
  12. ICML 2025Update Your Transformer to the Latest Release: Re-Basin of Task Vectors
  13. ICML 2025Vision-Language Models Create Cross-Modal Task Representations
  14. ICML 2025When can in-context learning generalize out of task distribution?
  15. ICML 2025Whoever Started the interference Should End It: Guiding Data-Free Model Merging via Task Vectors
  16. NeurIPS 2025$i$MIND: Insightful Multi-subject Invariant Neural Decoding
  17. NeurIPS 2025A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors
  18. NeurIPS 2025A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning
  19. NeurIPS 2025A Minimalistic Unified Framework for Incremental Learning across Image Restoration Tasks
  20. NeurIPS 2025A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings
  21. NeurIPS 2025Adaptable Safe Policy Learning from Multi-task Data with Constraint Prioritized Decision Transformer
  22. NeurIPS 2025AF-UMC: An Alignment-Free Fusion Framework for Unaligned Multi-View Clustering
  23. NeurIPS 2025Are Greedy Task Orderings Better Than Random in Continual Linear Regression?
  24. NeurIPS 2025Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners
  25. NeurIPS 2025Bit-swapping Oriented Twin-memory Multi-view Clustering in Lifelong Incomplete Scenarios
  26. NeurIPS 2025Cameras as Relative Positional Encoding
  27. NeurIPS 2025Can Class-Priors Help Single-Positive Multi-Label Learning?
  28. NeurIPS 2025Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?
  29. NeurIPS 2025Confidence-Aware With Prototype Alignment for Partial Multi-label Learning
  30. NeurIPS 2025Connecting Neural Models Latent Geometries with Relative Geodesic Representations
  31. NeurIPS 2025Constructing an Optimal Behavior Basis for the Option Keyboard
  32. NeurIPS 2025Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity
  33. NeurIPS 2025Continual Optimization with Symmetry Teleportation for Multi-Task Learning
  34. NeurIPS 2025Contribution of task-irrelevant stimuli to drift of neural representations
  35. NeurIPS 2025CSI-Bench: A Large-Scale In-the-Wild Dataset for Multi-task WiFi Sensing
  36. NeurIPS 2025DeepASA: An Object-Oriented Multi-Purpose Network for Auditory Scene Analysis
  37. NeurIPS 2025DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks
  38. NeurIPS 2025DINO-Foresight: Looking into the Future with DINO
  39. NeurIPS 2025Diversity-oriented Deep Multi-modal Clustering
  40. NeurIPS 2025Do different prompting methods yield a common task representation in language models?
  41. NeurIPS 2025EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretraining
  42. NeurIPS 2025Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddings
  43. NeurIPS 2025Exploring Tradeoffs through Mode Connectivity for Multi-Task Learning
  44. NeurIPS 2025Extracting task-relevant preserved dynamics from contrastive aligned neural recordings
  45. NeurIPS 2025Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes
  46. NeurIPS 2025Federated Continual Learning via Orchestrating Multi-Scale Expertise
  47. NeurIPS 2025Federated Multi-armed Bandits with Efficient Bit-Level Communications
  48. NeurIPS 2025FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts
  49. NeurIPS 2025FedRAM: Federated Reweighting and Aggregation for Multi-Task Learning
  50. NeurIPS 2025Find your Needle: Small Object Image Retrieval via Multi-Object Attention Optimization

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