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 485 篇，第 2 / 10 页

51. NeurIPS 2026Evaluating Whether LLMs Can Reliably Connect the DOTs?
52. NeurIPS 2026Event based Multi-Velocity-Scale Imaging
53. NeurIPS 2026EvoCodeBench: Evaluating Coding Agents in Multi-Turn Iterative Interactions
54. NeurIPS 2026Fair Bubble Sort: Provably Optimal Fair Ranking with Continuous Sensitive Attributes
55. NeurIPS 2026Few-shot Task Learning via Compositional Concept Inference
56. NeurIPS 2026FlashFFN: Multi-Head Decomposition Enables I/O-Aware Feed-Forward Network
57. NeurIPS 2026FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
58. NeurIPS 2026Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap
59. NeurIPS 2026Frequency-Structured Hamiltonian Neural Network for Multi-Timescale Dynamics
60. NeurIPS 2026From Detection to Understanding — A Multi-Task Dataset for Traffic Anomaly Reasoning
61. NeurIPS 2026Frontier Task Synthesis Via Solution-Centric Evolution
62. NeurIPS 2026Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness
63. NeurIPS 2026Goal-Conditioned Supervised Learning for Multi-Objective Recommendation
64. NeurIPS 2026Group Perspective Matters: Regulating Debate Relationships Can Mitigate Blind Conformity in Multi-Agent Debate
65. NeurIPS 2026Grouped Adaptive Head Mixing for Personalized Multi-Task Federated Reinforcement Learning
66. NeurIPS 2026Heterogeneous Judge-Aware Ranking with Sensitivity, Disagreement, and Confidence
67. NeurIPS 2026Hitting Time Isomorphism for Multi-Stage Planning with Foundation Policies
68. NeurIPS 2026Hydra: Towards Transferable Multi-Task Learning on Temporal Graphs
69. NeurIPS 2026Implicit Value Probing: Inferring Human Value Preferences via Strategic Multi-Turn Conversations
70. NeurIPS 2026Individuals Matter: Improving Deep Multi-View Clustering via Explicit Single-View Enhancement
71. NeurIPS 2026InfoFlow: A Framework for Multi-Layer Transformer Analysis
72. NeurIPS 2026Insight-Driven Search: A Framework for Multi-objective Automated Heuristic Design with Large Language Models
73. NeurIPS 2026InTAct: Interval-based Task Activation Consolidation for Continual Learning
74. NeurIPS 2026Interpretable Multiway-Split Trees
75. NeurIPS 2026Intrinsically Interpretable Attention via Sparse Post-Training
76. NeurIPS 2026Iterative ILP with Update-Size Control for Reducing Surrogate-Task Mismatch in Bit-Width Selection
77. NeurIPS 2026Jacobian Descent for Multi-Objective Optimization
78. NeurIPS 2026Justitia: Fair and Efficient Scheduling of Task-parallel LLM Agents with Selective Pampering
79. NeurIPS 2026Learning from Ranking Feedback: Improved Regret Bounds via Independence Preserving Rank Breaking
80. NeurIPS 2026Learning Unbiased Permutations via Flow Matching
81. NeurIPS 2026Likelihood-free inference of phylogenetic tree posterior distributions
82. NeurIPS 2026Local Policy Manifolds for Efficient Multi-Objective Reinforcement Learning
83. NeurIPS 2026Lyapunov-Driven Optimistic Learning for Online Scheduling with Multi-Stage Tasks
84. NeurIPS 2026MAdam: Metric-Aware Multi-Objective Adam
85. NeurIPS 2026MAGE: Towards Generalizable Multi-timescale EEG Representations
86. NeurIPS 2026MANGO:Multi-Angle Neural Gated Operators for Chirp-Perturbed PDEs
87. NeurIPS 2026Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systems
88. NeurIPS 2026Markov Metrical Task Systems
89. NeurIPS 2026MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models
90. NeurIPS 2026MC-H: Multi-Granularity Clustering with Hyperspherical Determinantal Point Process
91. NeurIPS 2026MC$^2$Mark: Distortion-Free Multi-Bit Watermarking for Long Messages
92. NeurIPS 2026MCAS: Signal-Processing-Based Multi-View Contrastive Learning for Acoustic Sensing
93. NeurIPS 2026MCPHunt: An Evaluation Framework for Cross-Boundary Data Propagation in Multi-Server MCP Agents
94. NeurIPS 2026Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios
95. NeurIPS 2026MemTailor: Hierarchical Memory-Augmented Multi-Expert Learning for Long-Tailed Recognition
96. NeurIPS 2026Mitigating Reward Hacking via Task Representations
97. NeurIPS 2026MLLM Makes Strong Backbone for Multi-Modal Object Detection
98. NeurIPS 2026MOBO-CAPS: Multi-objective Bayesian Optimization with Cardinality-Aware Pareto Selection
99. NeurIPS 2026Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideation
100. NeurIPS 2026MODULE: A Mutual-Promoting Deep Unfolding Framework Towards Degradation-Robust Multi-modal Image Fusion

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。