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 79 篇，第 1 / 2 页

1. ICLR 2026A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning
2. ICLR 2026AdaRank: Adaptive Rank Pruning for Enhanced Model Merging
3. ICLR 2026Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?
4. ICLR 2026Beyond Hearing: Learning Task-agnostic ExG Representations from Earphones via Physiology-informed Tokenization
5. ICLR 2026Beyond Simple Graphs: Neural Multi-Objective Routing on Multigraphs
6. ICLR 2026BoreaRL: A Multi-Objective Reinforcement Learning Environment for Climate-Adaptive Boreal Forest Management
7. ICLR 2026CatalystBench: A Comprehensive Multi-Task Benchmark for Advancing Language Models in Catalysis Science
8. ICLR 2026CircuitNet 3.0: A Multi-Modal Dataset with Task-Oriented Augmentation for AI-Driven Circuit Design
9. ICLR 2026Context Learning for Multi-Agent Discussion
10. ICLR 2026Cross-Embodiment Offline Reinforcement Learning for Heterogeneous Robot Datasets
11. ICLR 2026Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature
12. ICLR 2026Denoising Neural Reranker for Recommender Systems
13. ICLR 2026Diagnosing Failures in Generalization from Task-Relevant Representational Geometry
14. ICLR 2026Diffusion Blend: Inference-Time Multi-Preference Alignment for Diffusion Models
15. ICLR 2026Discovering Novel LLM Experts via Task-Capability Coevolution
16. ICLR 2026DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
17. ICLR 2026Domain Expansion: A Latent Space Construction Framework for Multi-Task Learning
18. ICLR 2026DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems
19. ICLR 2026Dual-Objective Reinforcement Learning with Novel Hamilton-Jacobi-Bellman Formulations
20. ICLR 2026Efficient Estimation of Kernel Surrogate Models for Task Attribution
21. ICLR 2026Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits
22. ICLR 2026Enhanced Continual Learning of Vision-Language Models with Model Fusion
23. ICLR 2026Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs
24. ICLR 2026Ensemble Prediction of Task Affinity for Efficient Multi-Task Learning
25. ICLR 2026EquAct: An SE(3)-Equivariant Multi-Task Transformer for 3D Robotic Manipulation
26. ICLR 2026Expressiveness of Multi-Neuron Convex Relaxations in Neural Network Certification
27. ICLR 2026FRABench and UFEval: Unified Fine-grained Evaluation with Task and Aspect Generalization
28. ICLR 2026From Embedding to Control: Representations for Stochastic Multi-Object Systems
29. ICLR 2026From Gradient Volume to Shapley Fairness: Towards Fair Multi-Task Learning
30. ICLR 2026G-Merging: Graph Models Merging for Parameter-Efficient Multi-Task Knowledge Consolidation
31. ICLR 2026GoalRank: Group-Relative Optimization for a Large Ranking Model
32. ICLR 2026Gradient-Sign Masking for Task Vector Transport Across Pre-Trained Models
33. ICLR 2026Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration
34. ICLR 2026GRO-RAG: Gradient-aware Re-rank Optimization for Multi-source Retrieval-Augmented Generation
35. ICLR 2026Hierarchical Multi-Scale Molecular Conformer Generation with Structural Awareness
36. ICLR 2026Hierarchical Multi-Stage Recovery Framework for Kronecker Compressed Sensing
37. ICLR 2026ICaRus: Identical Cache Reuse for Efficient Multi-Model Inference
38. ICLR 2026Kevin: Multi-Turn RL for Generating CUDA Kernels
39. ICLR 2026LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence
40. ICLR 2026LongHorizonUI: A Unified Framework for Robust long-horizon Task Automation of GUI Agent
41. ICLR 2026MASS: MoErging through Adaptive Subspace Selection
42. ICLR 2026MergOPT: A Merge-Aware Optimizer for Robust Model Merging
43. ICLR 2026MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
44. ICLR 2026MILPnet: A Multi-Scale Architecture with Geometric Feature Sequence Representations for Advancing MILP Problems
45. ICLR 2026Multi-Agent Debate with Memory Masking
46. ICLR 2026Multi-Armed Bandits with Minimum Aggregated Revenue Constraints
47. ICLR 2026Multi-Condition Conformal Selection
48. ICLR 2026Multi-Head Low-Rank Attention
49. ICLR 2026Multi-Marginal Flow Matching with Adversarially Learnt Interpolants
50. ICLR 2026Multi-modal Data Spectrum: Multi-modal Datasets are Multi-dimensional

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。