多任务排序论文趋势 2023–2026

主要结论

• 多任务排序论文从 2023 年的 252 篇增长到 2026 年的 480 篇，三年间扩大到约 1.9 倍。
• NeurIPS 是发多任务排序论文最多的会议，2023–2026 年共 485 篇，占四个会议总量的 34%。
• 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 8 篇增至 2026 年的 52 篇。
• 在「推荐与广告」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的点击率预测是 2.6 倍，多任务排序是 1.9 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 2026Adaptive Personalized Federated Learning via Multi-task Averaging of Kernel Mean Embeddings
• ICLR 2026Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?
• CVPR 2026A Supervised Multi-task Framework for Joint cryo-ET Restoration Enabled by
• 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 2025Balanced Ranking with Relative Centrality: A multi-core periphery perspective
• 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 2024Order-Preserving GFlowNets
• CVPR 2024Domain Separation Graph Neural Networks for Saliency Object Ranking
• NeurIPS 2023AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three Weeks
• ICML 2023Hypervolume Knowledge Gradient: A Lookahead Approach for Multi-Objective Bayesian Optimization with Partial Information
• 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 2026Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature
• CVPR 2026Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers

全部多任务排序论文

共 393 篇，第 2 / 8 页

51. CVPR 2025MangaNinja: Line Art Colorization with Precise Reference Following
52. CVPR 2025Medusa: A Multi-Scale High-order Contrastive Dual-Diffusion Approach for Multi-View Clustering
53. CVPR 2025MET3R: Measuring Multi-View Consistency in Generated Images
54. CVPR 2025MICAS: Multi-grained In-Context Adaptive Sampling for 3D Point Cloud Processing
55. CVPR 2025MLVU: Benchmarking Multi-task Long Video Understanding
56. CVPR 2025MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling
57. CVPR 2025MMRL: Multi-Modal Representation Learning for Vision-Language Models
58. CVPR 2025MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception
59. CVPR 2025MobileMamba: Lightweight Multi-Receptive Visual Mamba Network
60. CVPR 2025MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework
61. CVPR 2025Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture
62. CVPR 2025MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes
63. CVPR 2025Mr. DETR: Instructive Multi-Route Training for Detection Transformers
64. CVPR 2025Multi-Modal Aerial-Ground Cross-View Place Recognition with Neural ODEs
65. CVPR 2025Multi-Modal Synergistic Implicit Image Enhancement for Efficient Optical Flow Estimation
66. CVPR 2025Multi-modal Topology-embedded Graph Learning for Spatially Resolved Genes Prediction from Pathology Images with Prior Gene Similarity Information
67. CVPR 2025MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction
68. CVPR 2025MUSt3R: Multi-view Network for Stereo 3D Reconstruction
69. CVPR 2025MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D
70. CVPR 2025Omnidirectional Multi-Object Tracking
71. CVPR 2025PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches
72. CVPR 2025PDFactor: Learning Tri-Perspective View Policy Diffusion Field for Multi-Task Robotic Manipulation
73. CVPR 2025PHGC: Procedural Heterogeneous Graph Completion for Natural Language Task Verification in Egocentric Videos
74. CVPR 2025Pippo: High-Resolution Multi-View Humans from a Single Image
75. CVPR 2025ProHOC: Probabilistic Hierarchical Out-of-Distribution Classification via Multi-Depth Networks
76. CVPR 2025Resilient Sensor Fusion Under Adverse Sensor Failures via Multi-Modal Expert Fusion
77. CVPR 2025ROLL: Robust Noisy Pseudo-label Learning for Multi-View Clustering with Noisy Correspondence
78. CVPR 2025SocialGesture: Delving into Multi-person Gesture Understanding
79. CVPR 2025SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis
80. CVPR 2025TADFormer: Task-Adaptive Dynamic TransFormer for Efficient Multi-Task Learning
81. CVPR 2025Task Singular Vectors: Reducing Task Interference in Model Merging
82. CVPR 2025Task-Agnostic Guided Feature Expansion for Class-Incremental Learning
83. CVPR 2025Task-driven Image Fusion with Learnable Fusion Loss
84. CVPR 2025Test-Time Fine-Tuning of Image Compression Models for Multi-Task Adaptability
85. CVPR 2025Theory-Inspired Deep Multi-View Multi-Label Learning with Incomplete Views and Noisy Labels
86. CVPR 2025TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization
87. CVPR 2025Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters
88. CVPR 2025Towards Optimizing Large-Scale Multi-Graph Matching in Bioimaging
89. CVPR 2025Towards Universal Dataset Distillation via Task-Driven Diffusion
90. CVPR 2025Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation
91. CVPR 2025Understanding Multi-Task Activities from Single-Task Videos
92. CVPR 2025VL2Lite: Task-Specific Knowledge Distillation from Large Vision-Language Models to Lightweight Networks
93. CVPR 2025WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and Segmentation
94. CVPR 2025Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos
95. ICLR 2025A Statistical Framework for Ranking LLM-based Chatbots
96. ICLR 2025Accelerating Task Generalisation with Multi-Level Skill Hierarchies
97. ICLR 2025Active Task Disambiguation with LLMs
98. ICLR 2025Agent-Oriented Planning in Multi-Agent Systems
99. ICLR 2025Balanced Ranking with Relative Centrality: A multi-core periphery perspective
100. ICLR 2025BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts

常见问题

2023–2026 年四大会议一共有多少篇多任务排序论文？

共 1,440 篇，按年份分别是 2023 年 252 篇、2024 年 315 篇、2025 年 393 篇、2026 年 480 篇。

NeurIPS 2026 有多少篇多任务排序论文？

NeurIPS 2026 有 175 篇多任务排序论文，上一届是 144 篇。

ICLR 2026 有多少篇多任务排序论文？

ICLR 2026 有 79 篇多任务排序论文，上一届是 75 篇。

ICML 2026 有多少篇多任务排序论文？

ICML 2026 有 107 篇多任务排序论文，上一届是 80 篇。

CVPR 2026 有多少篇多任务排序论文？

CVPR 2026 有 119 篇多任务排序论文，上一届是 94 篇。

哪个会议的多任务排序论文最多？

NeurIPS，2023–2026 年共 485 篇。