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 20 / 24 页

  1. CVPR 2023OmniVidar: Omnidirectional Depth Estimation From Multi-Fisheye Images
  2. CVPR 2023Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction
  3. CVPR 2023PermutoSDF: Fast Multi-View Reconstruction With Implicit Surfaces Using Permutohedral Lattices
  4. CVPR 2023PersonNeRF: Personalized Reconstruction From Photo Collections
  5. CVPR 2023POEM: Reconstructing Hand in a Point Embedded Multi-View Stereo
  6. CVPR 2023Probing Neural Representations of Scene Perception in a Hippocampally Dependent Task Using Artificial Neural Networks
  7. CVPR 2023Quantum Multi-Model Fitting
  8. CVPR 2023Referring Multi-Object Tracking
  9. CVPR 2023Siamese DETR
  10. CVPR 2023Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks
  11. CVPR 2023Sparse Multi-Modal Graph Transformer With Shared-Context Processing for Representation Learning of Giga-Pixel Images
  12. CVPR 2023Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning
  13. CVPR 2023Task Residual for Tuning Vision-Language Models
  14. CVPR 2023TINC: Tree-Structured Implicit Neural Compression
  15. CVPR 2023TOPLight: Lightweight Neural Networks With Task-Oriented Pretraining for Visible-Infrared Recognition
  16. CVPR 2023Towards Domain Generalization for Multi-View 3D Object Detection in Bird-Eye-View
  17. CVPR 2023Towards Flexible Multi-Modal Document Models
  18. CVPR 2023Tunable Convolutions With Parametric Multi-Loss Optimization
  19. CVPR 2023Two-Way Multi-Label Loss
  20. CVPR 2023Understanding and Constructing Latent Modality Structures in Multi-Modal Representation Learning
  21. CVPR 2023Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection
  22. CVPR 2023Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving
  23. CVPR 2023Visual Prompt Multi-Modal Tracking
  24. CVPR 2023Why Is the Winner the Best?
  25. CVPR 2023WIRE: Wavelet Implicit Neural Representations
  26. ICLR 2023An Additive Instance-Wise Approach to Multi-class Model Interpretation
  27. ICLR 2023An Extensible Multi-modal Multi-task Object Dataset with Materials
  28. ICLR 2023BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection
  29. ICLR 2023Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels Only
  30. ICLR 2023Composite Slice Transformer: An Efficient Transformer with Composition of Multi-Scale Multi-Range Attentions
  31. ICLR 2023Compositional Task Representations for Large Language Models
  32. ICLR 2023Deep Learning on Implicit Neural Representations of Shapes
  33. ICLR 2023Editing models with task arithmetic
  34. ICLR 2023Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
  35. ICLR 2023Enhancing Meta Learning via Multi-Objective Soft Improvement Functions
  36. ICLR 2023Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning
  37. ICLR 2023Evaluating Representations with Readout Model Switching
  38. ICLR 2023Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation
  39. ICLR 2023f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation
  40. ICLR 2023HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers
  41. ICLR 2023How to prepare your task head for finetuning
  42. ICLR 2023HypeR: Multitask Hyper-Prompted Training Enables Large-Scale Retrieval Generalization
  43. ICLR 2023Investigating Multi-task Pretraining and Generalization in Reinforcement Learning
  44. ICLR 2023Is a Caption Worth a Thousand Images? A Study on Representation Learning
  45. ICLR 2023Learning Proximal Operators to Discover Multiple Optima
  46. ICLR 2023Learning topology-preserving data representations
  47. ICLR 2023Mitigating Memorization of Noisy Labels via Regularization between Representations
  48. ICLR 2023Multi-level Protein Structure Pre-training via Prompt Learning
  49. ICLR 2023Multi-objective optimization via equivariant deep hypervolume approximation
  50. ICLR 2023Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve

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