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 6 / 8 页

  1. NeurIPS 2024Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework
  2. NeurIPS 2024GO4Align: Group Optimization for Multi-Task Alignment
  3. NeurIPS 2024Goal Reduction with Loop-Removal Accelerates RL and Models Human Brain Activity in Goal-Directed Learning
  4. NeurIPS 2024GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks
  5. NeurIPS 2024Identifiable Shared Component Analysis of Unpaired Multimodal Mixtures
  6. NeurIPS 2024Improved Bayes Regret Bounds for Multi-Task Hierarchical Bayesian Bandit Algorithms
  7. NeurIPS 2024Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection
  8. NeurIPS 2024In-Context Learning with Representations: Contextual Generalization of Trained Transformers
  9. NeurIPS 2024Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse
  10. NeurIPS 2024Infer Induced Sentiment of Comment Response to Video: A New Task, Dataset and Baseline
  11. NeurIPS 2024Instruction Embedding: Latent Representations of Instructions Towards Task Identification
  12. NeurIPS 2024Kuro Siwo: 33 billion $m^2$ under the water. A global multi-temporal satellite dataset for rapid flood mapping
  13. NeurIPS 2024MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset
  14. NeurIPS 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
  15. NeurIPS 2024Multi-language Diversity Benefits Autoformalization
  16. NeurIPS 2024Multi-Scale Representation Learning for Protein Fitness Prediction
  17. NeurIPS 2024NanoBaseLib: A Multi-Task Benchmark Dataset for Nanopore Sequencing
  18. NeurIPS 2024Neural decoding from stereotactic EEG: accounting for electrode variability across subjects
  19. NeurIPS 2024Neural Persistence Dynamics
  20. NeurIPS 2024Pre-trained Large Language Models Use Fourier Features to Compute Addition
  21. NeurIPS 2024Propensity Score Alignment of Unpaired Multimodal Data
  22. NeurIPS 2024Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
  23. NeurIPS 2024Seek Commonality but Preserve Differences: Dissected Dynamics Modeling for Multi-modal Visual RL
  24. NeurIPS 2024Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models
  25. NeurIPS 2024SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query Benchmark
  26. NeurIPS 2024SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding
  27. NeurIPS 2024SureMap: Simultaneous mean estimation for single-task and multi-task disaggregated evaluation
  28. NeurIPS 2024Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning
  29. NeurIPS 2024TaskBench: Benchmarking Large Language Models for Task Automation
  30. NeurIPS 2024The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing
  31. NeurIPS 2024To Learn or Not to Learn, That is the Question — A Feature-Task Dual Learning Model of Perceptual Learning
  32. NeurIPS 2024Towards Multi-Domain Learning for Generalizable Video Anomaly Detection
  33. NeurIPS 2024TSDS: Data Selection for Task-Specific Model Finetuning
  34. NeurIPS 2024Understanding the Transferability of Representations via Task-Relatedness
  35. NeurIPS 2024UniTS: A Unified Multi-Task Time Series Model
  36. NeurIPS 2024Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression
  37. NeurIPS 2024Voxel Proposal Network via Multi-Frame Knowledge Distillation for Semantic Scene Completion
  38. NeurIPS 2024What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration
  39. NeurIPS 2023A Spectral Algorithm for List-Decodable Covariance Estimation in Relative Frobenius Norm
  40. NeurIPS 2023AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three Weeks
  41. NeurIPS 2023Achieving Cross Modal Generalization with Multimodal Unified Representation
  42. NeurIPS 2023Active Bipartite Ranking
  43. NeurIPS 2023Active representation learning for general task space with applications in robotics
  44. NeurIPS 2023Addressing Negative Transfer in Diffusion Models
  45. NeurIPS 2023Agnostic Multi-Group Active Learning
  46. NeurIPS 2023AIMS: All-Inclusive Multi-Level Segmentation for Anything
  47. NeurIPS 2023An active learning framework for multi-group mean estimation
  48. NeurIPS 2023Analysis of Variance of Multiple Causal Networks
  49. NeurIPS 2023Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent
  50. NeurIPS 2023Bandit Social Learning under Myopic Behavior

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