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 57 篇，第 1 / 2 页

1. ICLR 2026Adaptive Test-Time Training for Predicting Need for Invasive Mechanical Ventilation in Multi-Center Cohorts
2. ICLR 2026Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?
3. ICLR 2026Beyond Hearing: Learning Task-agnostic ExG Representations from Earphones via Physiology-informed Tokenization
4. ICLR 2026Beyond Uniformity: Regularizing Implicit Neural Representations through a Lipschitz Lens
5. ICLR 2026Calibrated Information Bottleneck for Trusted Multi-modal Clustering
6. ICLR 2026CatalystBench: A Comprehensive Multi-Task Benchmark for Advancing Language Models in Catalysis Science
7. ICLR 2026Chain-of-Context Learning: Dynamic Constraint Understanding for Multi-Task VRPs
8. ICLR 2026CircuitNet 3.0: A Multi-Modal Dataset with Task-Oriented Augmentation for AI-Driven Circuit Design
9. ICLR 2026Combination-of-Experts with Knowledge Sharing for Cross-Task Vehicle Routing Problems
10. ICLR 2026Coupled Transformer Autoencoder for Disentangling Multi-Region Neural Latent Dynamics
11. ICLR 2026Cross-Domain Lossy Compression via Rate- and Classification-Constrained Optimal Transport
12. ICLR 2026Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature
13. ICLR 2026DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
14. ICLR 2026Domain Expansion: A Latent Space Construction Framework for Multi-Task Learning
15. ICLR 2026Dual Goal Representations
16. ICLR 2026Dual-Branch Representations with Dynamic Gated Fusion and Triple-Granularity Alignment for Deep Multi-View Clustering
17. ICLR 2026Emergent Coordination in Multi-Agent Language Models
18. ICLR 2026Enhanced Continual Learning of Vision-Language Models with Model Fusion
19. ICLR 2026Ensemble Prediction of Task Affinity for Efficient Multi-Task Learning
20. ICLR 2026EquAct: An SE(3)-Equivariant Multi-Task Transformer for 3D Robotic Manipulation
21. ICLR 2026From Embedding to Control: Representations for Stochastic Multi-Object Systems
22. ICLR 2026From Gradient Volume to Shapley Fairness: Towards Fair Multi-Task Learning
23. ICLR 2026G-Merging: Graph Models Merging for Parameter-Efficient Multi-Task Knowledge Consolidation
24. ICLR 2026GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion Perception
25. ICLR 2026Gradient-Sign Masking for Task Vector Transport Across Pre-Trained Models
26. ICLR 2026GUIDE: Gated Uncertainty-Informed Disentangled Experts for Long-tailed Recognition
27. ICLR 2026Hierarchical Multi-Scale Molecular Conformer Generation with Structural Awareness
28. ICLR 2026Hierarchical Multi-Stage Recovery Framework for Kronecker Compressed Sensing
29. ICLR 2026Incomplete Multi-View Multi-Label Classification via Shared Codebook and Fused-Teacher Self-Distillation
30. ICLR 2026Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry
31. ICLR 2026Learning Domain-Aware Task Prompt Representations for Multi-Domain All-in-One Image Restoration
32. ICLR 2026Learning Recursive Multi-Scale Representations for Irregular Multivariate Time Series Forecasting
33. ICLR 2026Low rank adaptation of chemical foundation models generate effective odorant representations
34. ICLR 2026MASS: MoErging through Adaptive Subspace Selection
35. ICLR 2026MergOPT: A Merge-Aware Optimizer for Robust Model Merging
36. ICLR 2026MILPnet: A Multi-Scale Architecture with Geometric Feature Sequence Representations for Advancing MILP Problems
37. ICLR 2026Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?
38. ICLR 2026MotionWeaver: Holistic 4D-Anchored Framework for Multi-Humanoid Image Animation
39. ICLR 2026Multi-Condition Conformal Selection
40. ICLR 2026Multi-Feature Quantized Self-Attention for Fair Large Language Models
41. ICLR 2026Multi-Head Low-Rank Attention
42. ICLR 2026Multi-Marginal Flow Matching with Adversarially Learnt Interpolants
43. ICLR 2026Multi-modal Data Spectrum: Multi-modal Datasets are Multi-dimensional
44. ICLR 2026Multi-Task Low-Rank Model Adaptation
45. ICLR 2026Navigating the Accuracy-Size Trade-Off with Flexible Model Merging
46. ICLR 2026Neural Collapse in Multi-Task Learning
47. ICLR 2026Permutation-Consistent Variational Encoding for Incomplete Multi-View Multi-Label Classification
48. ICLR 2026PERSISTENCE SPHERES: BI-CONTINUOUS REPRESENTATIONS OF PERSISTENCE DIAGRAMS.
49. ICLR 2026PoinnCARE: Hyperbolic Multi-Modal Learning for Enzyme Classification
50. ICLR 2026Protein Structure Tokenization via Geometric Byte Pair Encoding

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。