多任务学习论文趋势 2023–2026

主要结论

• 多任务学习论文从 2023 年的 288 篇增长到 2026 年的 402 篇，三年间扩大到约 1.4 倍。
• NeurIPS 是发多任务学习论文最多的会议，2023–2026 年共 399 篇，占四个会议总量的 34%。
• 交叉方向里涨得最快的是数据集与基准：同时属于两个主题的论文从 2023 年的 6 篇增至 2026 年的 16 篇。
• 在「元学习与迁移」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的基础模型适配是 3.8 倍，多任务学习是 1.4 倍。

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

• NeurIPS 2026A Mahalanobis Margin \texorpdfstring{$\gamma_{\min}$}{gamma\_min} Bound on Task Confusion in Pretrained Class-Incremental Learning: From Infeasibility to Exponential Attenuation
• ICML 2026A Systematic Study of Behavioral Cloning for Scientific Data Annotation
• ICLR 2026Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?
• CVPR 20263D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding
• NeurIPS 2025A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning
• ICML 2025ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning
• ICLR 2025CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs
• CVPR 2025ACAttack: Adaptive Cross Attacking RGB-T Tracker via Multi-Modal Response Decoupling
• NeurIPS 2024CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding
• ICML 2024Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning
• ICLR 2024Class Incremental Learning via Likelihood Ratio Based Task Prediction
• CVPR 2024Differentiable Information Bottleneck for Deterministic Multi-view Clustering
• NeurIPS 2023A Spectral Algorithm for List-Decodable Covariance Estimation in Relative Frobenius Norm
• ICML 2023A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imaging
• ICLR 2023An Extensible Multi-modal Multi-task Object Dataset with Materials
• CVPR 2023AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation
• NeurIPS 2026A Scalable Multi-Task Model for Virtual Sensors
• ICML 2026Alleviating Observation Bias via Causal-Invariant Meta-Learning for Unbalanced Incomplete Multi-view Clustering
• ICLR 2026Beyond Hearing: Learning Task-agnostic ExG Representations from Earphones via Physiology-informed Tokenization
• CVPR 2026Any Resolution Any Geometry From Multi-View To Multi-Patch

全部多任务学习论文

共 288 篇，第 2 / 6 页

51. CVPR 2023Multi-View Azimuth Stereo via Tangent Space Consistency
52. CVPR 2023Multi-View Reconstruction Using Signed Ray Distance Functions (SRDF)
53. CVPR 2023MVImgNet: A Large-Scale Dataset of Multi-View Images
54. CVPR 2023NeAT: Learning Neural Implicit Surfaces With Arbitrary Topologies From Multi-View Images
55. CVPR 2023NeuFace: Realistic 3D Neural Face Rendering From Multi-View Images
56. CVPR 2023Neural Pixel Composition for 3D-4D View Synthesis From Multi-Views
57. CVPR 2023NeuralPCI: Spatio-Temporal Neural Field for 3D Point Cloud Multi-Frame Non-Linear Interpolation
58. CVPR 2023OmniVidar: Omnidirectional Depth Estimation From Multi-Fisheye Images
59. CVPR 2023Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction
60. CVPR 2023PermutoSDF: Fast Multi-View Reconstruction With Implicit Surfaces Using Permutohedral Lattices
61. CVPR 2023PersonNeRF: Personalized Reconstruction From Photo Collections
62. CVPR 2023POEM: Reconstructing Hand in a Point Embedded Multi-View Stereo
63. CVPR 2023Probing Neural Representations of Scene Perception in a Hippocampally Dependent Task Using Artificial Neural Networks
64. CVPR 2023Quantum Multi-Model Fitting
65. CVPR 2023Referring Multi-Object Tracking
66. CVPR 2023Siamese DETR
67. CVPR 2023Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks
68. CVPR 2023Sparse Multi-Modal Graph Transformer With Shared-Context Processing for Representation Learning of Giga-Pixel Images
69. CVPR 2023Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning
70. CVPR 2023Task Residual for Tuning Vision-Language Models
71. CVPR 2023TINC: Tree-Structured Implicit Neural Compression
72. CVPR 2023TOPLight: Lightweight Neural Networks With Task-Oriented Pretraining for Visible-Infrared Recognition
73. CVPR 2023Towards Domain Generalization for Multi-View 3D Object Detection in Bird-Eye-View
74. CVPR 2023Towards Flexible Multi-Modal Document Models
75. CVPR 2023Tunable Convolutions With Parametric Multi-Loss Optimization
76. CVPR 2023Two-Way Multi-Label Loss
77. CVPR 2023Understanding and Constructing Latent Modality Structures in Multi-Modal Representation Learning
78. CVPR 2023Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection
79. CVPR 2023Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving
80. CVPR 2023Visual Prompt Multi-Modal Tracking
81. CVPR 2023Why Is the Winner the Best?
82. CVPR 2023WIRE: Wavelet Implicit Neural Representations
83. ICLR 2023An Additive Instance-Wise Approach to Multi-class Model Interpretation
84. ICLR 2023An Extensible Multi-modal Multi-task Object Dataset with Materials
85. ICLR 2023BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection
86. ICLR 2023Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels Only
87. ICLR 2023Composite Slice Transformer: An Efficient Transformer with Composition of Multi-Scale Multi-Range Attentions
88. ICLR 2023Compositional Task Representations for Large Language Models
89. ICLR 2023Deep Learning on Implicit Neural Representations of Shapes
90. ICLR 2023Editing models with task arithmetic
91. ICLR 2023Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
92. ICLR 2023Enhancing Meta Learning via Multi-Objective Soft Improvement Functions
93. ICLR 2023Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning
94. ICLR 2023Evaluating Representations with Readout Model Switching
95. ICLR 2023Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation
96. ICLR 2023f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation
97. ICLR 2023HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers
98. ICLR 2023How to prepare your task head for finetuning
99. ICLR 2023HypeR: Multitask Hyper-Prompted Training Enables Large-Scale Retrieval Generalization
100. ICLR 2023Investigating Multi-task Pretraining and Generalization in Reinforcement Learning

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。