多任务排序论文趋势 2023–2026

多目标排序

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,440 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

多任务排序论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202356585583252
20241103867100315
2025144758094393
202617579107119480

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

全部多任务排序论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 393 篇，第 5 / 8 页

  1. ICML 2025Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization
  2. ICML 2025How Much Can Transfer? BRIDGE: Bounded Multi-Domain Graph Foundation Model with Generalization Guarantees
  3. ICML 2025How to Train Your Multi-Exit Model? Analyzing the Impact of Training Strategies
  4. ICML 2025Implicit degree bias in the link prediction task
  5. ICML 2025Improved Theoretically-Grounded Evolutionary Algorithms for Subset Selection with a Linear Cost Constraint
  6. ICML 2025Improving Your Model Ranking on Chatbot Arena by Vote Rigging
  7. ICML 2025Learngene Tells You How to Customize: Task-Aware Parameter Initialization at Flexible Scales
  8. ICML 2025Learning Cascade Ranking as One Network
  9. ICML 2025Learning Compact Semantic Information for Incomplete Multi-View Missing Multi-Label Classification
  10. ICML 2025Learning Configurations for Data-Driven Multi-Objective Optimization
  11. ICML 2025Learning Fused State Representations for Control from Multi-View Observations
  12. ICML 2025Learning With Multi-Group Guarantees For Clusterable Subpopulations
  13. ICML 2025LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
  14. ICML 2025Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer
  15. ICML 2025MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning
  16. ICML 2025Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation
  17. ICML 2025Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
  18. ICML 2025MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement Learning
  19. ICML 2025MoH: Multi-Head Attention as Mixture-of-Head Attention
  20. ICML 2025MTL-UE: Learning to Learn Nothing for Multi-Task Learning
  21. ICML 2025Multi-Objective Causal Bayesian Optimization
  22. ICML 2025Multi-objective Linear Reinforcement Learning with Lexicographic Rewards
  23. ICML 2025Multi-Session Budget Optimization for Forward Auction-based Federated Learning
  24. ICML 2025Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning
  25. ICML 2025Navigating the Social Welfare Frontier: Portfolios for Multi-objective Reinforcement Learning
  26. ICML 2025No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
  27. ICML 2025Optimal Task Order for Continual Learning of Multiple Tasks
  28. ICML 2025Optimizing Temperature for Language Models with Multi-Sample Inference
  29. ICML 2025Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner
  30. ICML 2025Pairwise Maximum Likelihood For Multi-Class Logistic Regression Model With Multiple Rare Classes
  31. ICML 2025Pareto Merging: Multi-Objective Optimization for Preference-Aware Model Merging
  32. ICML 2025Pareto-frontier Entropy Search with Variational Lower Bound Maximization
  33. ICML 2025PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model
  34. ICML 2025PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion
  35. ICML 2025Preference Controllable Reinforcement Learning with Advanced Multi-Objective Optimization
  36. ICML 2025PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering
  37. ICML 2025Provable In-Context Vector Arithmetic via Retrieving Task Concepts
  38. ICML 2025Ranking with Multiple Oracles: From Weak to Strong Stochastic Transitivity
  39. ICML 2025Robust Consensus Anchor Learning for Efficient Multi-view Subspace Clustering
  40. ICML 2025S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking
  41. ICML 2025SHIELD: Multi-task Multi-distribution Vehicle Routing Solver with Sparsity and Hierarchy
  42. ICML 2025Super Deep Contrastive Information Bottleneck for Multi-modal Clustering
  43. ICML 2025Task Generalization with Autoregressive Compositional Structure: Can Learning from $D$ Tasks Generalize to $D^T$ Tasks?
  44. ICML 2025Task-Gated Multi-Expert Collaboration Network for Degraded Multi-Modal Image Fusion
  45. ICML 2025Tuning LLM Judge Design Decisions for 1/1000 of the Cost
  46. ICML 2025Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods
  47. ICML 2025Update Your Transformer to the Latest Release: Re-Basin of Task Vectors
  48. ICML 2025When can in-context learning generalize out of task distribution?
  49. ICML 2025Whoever Started the interference Should End It: Guiding Data-Free Model Merging via Task Vectors
  50. NeurIPS 2025A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查多任务排序在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "multi-task-ranking"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「推荐与广告」下的其他主题