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 264 篇，第 3 / 6 页

  1. ICLR 2025Multi-Resolution Decomposable Diffusion Model for Non-Stationary Time Series Anomaly Detection
  2. ICLR 2025Multi-session, multi-task neural decoding from distinct cell-types and brain regions
  3. ICLR 2025Multi-Task Dense Predictions via Unleashing the Power of Diffusion
  4. ICLR 2025NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals
  5. ICLR 2025Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences
  6. ICLR 2025Perm: A Parametric Representation for Multi-Style 3D Hair Modeling
  7. ICLR 2025Rethinking Neural Multi-Objective Combinatorial Optimization via Neat Weight Embedding
  8. ICLR 2025REVISITING MULTI-PERMUTATION EQUIVARIANCE THROUGH THE LENS OF IRREDUCIBLE REPRESENTATIONS
  9. ICLR 2025Selective Task Group Updates for Multi-Task Optimization
  10. ICLR 2025SpaceGNN: Multi-Space Graph Neural Network for Node Anomaly Detection with Extremely Limited Labels
  11. ICLR 2025STAFF: Speculative Coreset Selection for Task-Specific Fine-tuning
  12. ICLR 2025Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning
  13. ICLR 2025Task Descriptors Help Transformers Learn Linear Models In-Context
  14. ICLR 2025Towards Optimal Multi-draft Speculative Decoding
  15. ICLR 2025When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
  16. ICLR 2025Which Tasks Should Be Compressed Together? A Causal Discovery Approach for Efficient Multi-Task Representation Compression
  17. ICML 2025A General Representation-Based Approach to Multi-Source Domain Adaptation
  18. ICML 2025A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
  19. ICML 2025A Mixed-Curvature based Pre-training Paradigm for Multi-Task Vehicle Routing Solver
  20. ICML 2025A Multi-Region Brain Model to Elucidate the Role of Hippocampus in Spatially Embedded Decision-Making
  21. ICML 2025A Two-Stage Learning-to-Defer Approach for Multi-Task Learning
  22. ICML 2025Active Fine-Tuning of Multi-Task Policies
  23. ICML 2025Algorithm Development in Neural Networks: Insights from the Streaming Parity Task
  24. ICML 2025ARS: Adaptive Reward Scaling for Multi-Task Reinforcement Learning
  25. ICML 2025ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning
  26. ICML 2025Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning
  27. ICML 2025Bifurcate then Alienate: Incomplete Multi-view Clustering via Coupled Distribution Learning with Linear Overhead
  28. ICML 2025CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention
  29. ICML 2025CALM: Consensus-Aware Localized Merging for Multi-Task Learning
  30. ICML 2025CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging
  31. ICML 2025Deep Fuzzy Multi-view Learning for Reliable Classification
  32. ICML 2025Drug-TTA: Test-Time Adaptation for Drug Virtual Screening via Multi-task Meta-Auxiliary Learning
  33. ICML 2025Efficient Federated Incomplete Multi-View Clustering
  34. ICML 2025Fast Incomplete Multi-view Clustering by Flexible Anchor Learning
  35. ICML 2025FEAT-KD: Learning Concise Representations for Single and Multi-Target Regression via TabNet Knowledge Distillation
  36. ICML 2025Federated Incomplete Multi-view Clustering with Globally Fused Graph Guidance
  37. ICML 2025FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making
  38. ICML 2025From Spectrum-free towards Baseline-view-free: Double-track Proximity Driven Multi-view Clustering
  39. ICML 2025From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining
  40. ICML 2025Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning
  41. ICML 2025Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens
  42. ICML 2025Learngene Tells You How to Customize: Task-Aware Parameter Initialization at Flexible Scales
  43. ICML 2025Learning Compact Semantic Information for Incomplete Multi-View Missing Multi-Label Classification
  44. ICML 2025Learning Fused State Representations for Control from Multi-View Observations
  45. ICML 2025Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation
  46. ICML 2025Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
  47. ICML 2025MTL-UE: Learning to Learn Nothing for Multi-Task Learning
  48. ICML 2025Multi-Session Budget Optimization for Forward Auction-based Federated Learning
  49. ICML 2025Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning
  50. ICML 2025On the Adversarial Robustness of Multi-Kernel Clustering

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