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 18 / 24 页

  1. NeurIPS 2024Exploring the Precise Dynamics of Single-Layer GAN Models: Leveraging Multi-Feature Discriminators for High-Dimensional Subspace Learning
  2. NeurIPS 2024Extending Multi-modal Contrastive Representations
  3. NeurIPS 2024Flexible task abstractions emerge in linear networks with fast and bounded units
  4. NeurIPS 2024GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidance
  5. NeurIPS 2024Generative Retrieval Meets Multi-Graded Relevance
  6. NeurIPS 2024Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework
  7. NeurIPS 2024GO4Align: Group Optimization for Multi-Task Alignment
  8. NeurIPS 2024Goal Reduction with Loop-Removal Accelerates RL and Models Human Brain Activity in Goal-Directed Learning
  9. NeurIPS 2024GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks
  10. NeurIPS 2024Identifiable Shared Component Analysis of Unpaired Multimodal Mixtures
  11. NeurIPS 2024Improved Bayes Regret Bounds for Multi-Task Hierarchical Bayesian Bandit Algorithms
  12. NeurIPS 2024Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection
  13. NeurIPS 2024In-Context Learning with Representations: Contextual Generalization of Trained Transformers
  14. NeurIPS 2024Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse
  15. NeurIPS 2024Infer Induced Sentiment of Comment Response to Video: A New Task, Dataset and Baseline
  16. NeurIPS 2024Instruction Embedding: Latent Representations of Instructions Towards Task Identification
  17. NeurIPS 2024Kuro Siwo: 33 billion $m^2$ under the water. A global multi-temporal satellite dataset for rapid flood mapping
  18. NeurIPS 2024MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset
  19. NeurIPS 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
  20. NeurIPS 2024Multi-language Diversity Benefits Autoformalization
  21. NeurIPS 2024Multi-Scale Representation Learning for Protein Fitness Prediction
  22. NeurIPS 2024NanoBaseLib: A Multi-Task Benchmark Dataset for Nanopore Sequencing
  23. NeurIPS 2024Neural decoding from stereotactic EEG: accounting for electrode variability across subjects
  24. NeurIPS 2024Neural Persistence Dynamics
  25. NeurIPS 2024Pre-trained Large Language Models Use Fourier Features to Compute Addition
  26. NeurIPS 2024Propensity Score Alignment of Unpaired Multimodal Data
  27. NeurIPS 2024Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
  28. NeurIPS 2024Seek Commonality but Preserve Differences: Dissected Dynamics Modeling for Multi-modal Visual RL
  29. NeurIPS 2024Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models
  30. NeurIPS 2024SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query Benchmark
  31. NeurIPS 2024SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding
  32. NeurIPS 2024SureMap: Simultaneous mean estimation for single-task and multi-task disaggregated evaluation
  33. NeurIPS 2024Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning
  34. NeurIPS 2024TaskBench: Benchmarking Large Language Models for Task Automation
  35. NeurIPS 2024The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing
  36. NeurIPS 2024To Learn or Not to Learn, That is the Question — A Feature-Task Dual Learning Model of Perceptual Learning
  37. NeurIPS 2024Towards Multi-Domain Learning for Generalizable Video Anomaly Detection
  38. NeurIPS 2024TSDS: Data Selection for Task-Specific Model Finetuning
  39. NeurIPS 2024Understanding the Transferability of Representations via Task-Relatedness
  40. NeurIPS 2024UniTS: A Unified Multi-Task Time Series Model
  41. NeurIPS 2024Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression
  42. NeurIPS 2024Voxel Proposal Network via Multi-Frame Knowledge Distillation for Semantic Scene Completion
  43. NeurIPS 2024What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration
  44. CVPR 2023(ML)$^2$P-Encoder: On Exploration of Channel-Class Correlation for Multi-Label Zero-Shot Learning
  45. CVPR 2023A Light Touch Approach to Teaching Transformers Multi-View Geometry
  46. CVPR 2023AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation
  47. CVPR 2023Batch Model Consolidation: A Multi-Task Model Consolidation Framework
  48. CVPR 2023BiCro: Noisy Correspondence Rectification for Multi-Modality Data via Bi-Directional Cross-Modal Similarity Consistency
  49. CVPR 2023Bridging the Gap Between Model Explanations in Partially Annotated Multi-Label Classification
  50. CVPR 2023Chat2Map: Efficient Scene Mapping From Multi-Ego Conversations

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