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 75 篇，第 1 / 2 页

1. ICLR 2025A Statistical Framework for Ranking LLM-based Chatbots
2. ICLR 2025Accelerating Task Generalisation with Multi-Level Skill Hierarchies
3. ICLR 2025Active Task Disambiguation with LLMs
4. ICLR 2025Agent-Oriented Planning in Multi-Agent Systems
5. ICLR 2025Balanced Ranking with Relative Centrality: A multi-core periphery perspective
6. ICLR 2025BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts
7. ICLR 2025BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL
8. ICLR 2025CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation
9. ICLR 2025CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs
10. ICLR 2025ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks
11. ICLR 2025Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning
12. ICLR 2025CREIMBO: Cross-Regional Ensemble Interactions in Multi-view Brain Observations
13. ICLR 2025DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL
14. ICLR 2025Denoising Task Difficulty-based Curriculum for Training Diffusion Models
15. ICLR 2025DEPT: Decoupled Embeddings for Pre-training Language Models
16. ICLR 2025Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models
17. ICLR 2025Efficient Discovery of Pareto Front for Multi-Objective Reinforcement Learning
18. ICLR 2025Efficient Low-Bit Quantization with Adaptive Scales for Multi-Task Co-Training
19. ICLR 2025EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents
20. ICLR 2025Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimization
21. ICLR 2025Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic
22. ICLR 2025GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning
23. ICLR 2025HMoRA: Making LLMs More Effective with Hierarchical Mixture of LoRA Experts
24. ICLR 2025Holographic Node Representations: Pre-training Task-Agnostic Node Embeddings
25. ICLR 2025How to Find the Exact Pareto Front for Multi-Objective MDPs?
26. ICLR 2025ILLUSION: Unveiling Truth with a Comprehensive Multi-Modal, Multi-Lingual Deepfake Dataset
27. ICLR 2025InstantPortrait: One-Step Portrait Editing via Diffusion Multi-Objective Distillation
28. ICLR 2025It Helps to Take a Second Opinion: Teaching Smaller LLMs To Deliberate Mutually via Selective Rationale Optimisation
29. ICLR 2025Joint Gradient Balancing for Data Ordering in Finite-Sum Multi-Objective Optimization
30. ICLR 2025Learned Reference-based Diffusion Sampler for multi-modal distributions
31. ICLR 2025Learning Diagrams: A Graphical Language for Compositional Training Regimes
32. ICLR 2025Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics
33. ICLR 2025Learning to Help in Multi-Class Settings
34. ICLR 2025Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs
35. ICLR 2025Leveraging Variable Sparsity to Refine Pareto Stationarity in Multi-Objective Optimization
36. ICLR 2025LiveXiv - A Multi-Modal live benchmark based on Arxiv papers content
37. ICLR 2025Many-Objective Multi-Solution Transport
38. ICLR 2025MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation
39. ICLR 2025MAP: Multi-Human-Value Alignment Palette
40. ICLR 2025Mastering Task Arithmetic: $\tau$Jp as a Key Indicator for Weight Disentanglement
41. ICLR 2025MGDA Converges under Generalized Smoothness, Provably
42. ICLR 2025Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning
43. ICLR 2025Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace
44. ICLR 2025MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra
45. ICLR 2025MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations
46. ICLR 2025Multi-Dimensional Conformal Prediction
47. ICLR 2025Multi-Label Node Classification with Label Influence Propagation
48. ICLR 2025Multi-objective Differentiable Neural Architecture Search
49. ICLR 2025Multi-session, multi-task neural decoding from distinct cell-types and brain regions
50. ICLR 2025Multi-Task Dense Predictions via Unleashing the Power of Diffusion

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。