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 126 篇，第 2 / 3 页

51. NeurIPS 2026How Data Augmentation Shapes Neural Representations
52. NeurIPS 2026HRIL: Isolating Multimodal Synergy via Higher-Order Dependence
53. NeurIPS 2026Hydra: Towards Transferable Multi-Task Learning on Temporal Graphs
54. NeurIPS 2026HyperSkill: Multi-Modal Skill Learning on the Unit Hypersphere
55. NeurIPS 2026Individuals Matter: Improving Deep Multi-View Clustering via Explicit Single-View Enhancement
56. NeurIPS 2026Insight-Driven Search: A Framework for Multi-objective Automated Heuristic Design with Large Language Models
57. NeurIPS 2026InTAct: Interval-based Task Activation Consolidation for Continual Learning
58. NeurIPS 2026Iterative ILP with Update-Size Control for Reducing Surrogate-Task Mismatch in Bit-Width Selection
59. NeurIPS 2026Justitia: Fair and Efficient Scheduling of Task-parallel LLM Agents with Selective Pampering
60. NeurIPS 2026Laplacian Heads Improve Transformers by Smoothing Token Representations
61. NeurIPS 2026Learning Interpretable Switching Dynamics in Shared Neural-Behavioral Latent Space
62. NeurIPS 2026Learning Task-Centric World Models from Visual Foundations
63. NeurIPS 2026Learning What to Predict: Downstream-Guided Task Design for Continued Pretraining
64. NeurIPS 2026LoRASpace: A Pool-Wide Shared Substrate for Static and Dynamic Multi-LoRA Composition
65. NeurIPS 2026MAdam: Metric-Aware Multi-Objective Adam
66. NeurIPS 2026MAGE: Towards Generalizable Multi-timescale EEG Representations
67. NeurIPS 2026MaRiO: Multi-agent Collaborative Reasoning via Shared Observations in MLLMs
68. NeurIPS 2026Market-Based Runtime Resource Allocation for LLM Multi-Agent Systems
69. NeurIPS 2026Markov Metrical Task Systems
70. NeurIPS 2026MC-H: Multi-Granularity Clustering with Hyperspherical Determinantal Point Process
71. NeurIPS 2026MCAS: Signal-Processing-Based Multi-View Contrastive Learning for Acoustic Sensing
72. NeurIPS 2026Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios
73. NeurIPS 2026Mitigating Reward Hacking via Task Representations
74. NeurIPS 2026MLLM Makes Strong Backbone for Multi-Modal Object Detection
75. NeurIPS 2026MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing
76. NeurIPS 2026Multi-agent Collaboration with State Management
77. NeurIPS 2026Multi-Agent Coordination via Support-Preserving Distillation
78. NeurIPS 2026Multi-Constrained Randomized Smoothing Certificates
79. NeurIPS 2026Multi-Environment POMDPs with Finite-Horizon Objectives
80. NeurIPS 2026Multi-Level Alignment Framework for Long-Term Olfactory Neural Decoding
81. NeurIPS 2026Multi-Part Object Representations via Graph Structures and Co-Part Discovery
82. NeurIPS 2026Multi-Turn RL Makes Small Language Model Competitive for Optimization Modeling
83. NeurIPS 2026MUSS: A Multi-scale and Sequence-based Model for Single-cell Gene Regulation
84. NeurIPS 2026MvFFN: Multi-view Floor-Plan Feed-Forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction
85. NeurIPS 2026Narrowing the Collaboration Gap, Probably
86. NeurIPS 2026Near-Optimal Learning in Parametric Bandits with Action-Dependent Coarsened Feedback
87. NeurIPS 2026Noise-Level KL Rates for Multi-Marginal Schrödinger Bridge Surrogates
88. NeurIPS 2026OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
89. NeurIPS 2026ORCA: Orthogonal Residual Consensus Alignment for Multi-View Clustering
90. NeurIPS 2026OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism
91. NeurIPS 2026Permutation Sensitivity in t-SVD-based Multi-view Clustering
92. NeurIPS 2026PGSB: Pretrained-Guided Shared Basis for LoRA Model Merging
93. NeurIPS 2026Physical AI Smart Spaces: A Large-Scale Benchmark for Multi-Camera 3D Perception in Smart Spaces
94. NeurIPS 2026Platonic Task Arithmetic
95. NeurIPS 2026Position: Fair Representations Cannot Hold What They Promise
96. NeurIPS 2026Position: Lottery Tickets Do Not Explain Overparameterization. How About Escape Dimensions?
97. NeurIPS 2026ProbMedTOD: A Bayesian Network Guided Task-Oriented Dialogue System for Patient History Taking
98. NeurIPS 2026RAMA: Resistance-Aware Multi-Hop Aggregation Graph Representation Learning for Robust Ethereum Account Classification
99. NeurIPS 2026Releasing Anchors from Cross-View Correspondence: Probabilistic Multi-View Anchor Graph Clustering
100. NeurIPS 2026ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models

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。