多任务学习论文趋势 2023–2026

共享表示

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,181 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

多任务学习论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023111435282288
202461315877227
2025101404776264
20261265791128402

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

全部多任务学习论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,181 篇，第 7 / 24 页

  1. NeurIPS 2026CoDeRNet: Selective Cross-Task Routing under Heterogeneous Supervision for Change Detection and Captioning
  2. NeurIPS 2026Compressible Representations: Functional Spines in Deep Neural Networks
  3. NeurIPS 2026Constructive Neural Policies for the Quadratic Assignment Problem via Multi-Expert Imitation
  4. NeurIPS 2026Cross-Family Universality of Behavioral Axes via Anchor-Projected Representations
  5. NeurIPS 2026Cross-User Poisoning: User-Task Boundary Failures in Multi-User Collaborative Language Agents
  6. NeurIPS 2026Crowded in B-Space: Calibrating Shared Directions for LoRA Merging
  7. NeurIPS 2026Curvature-Guided Parameter Initialization for Multi-Task Learning
  8. NeurIPS 2026Cyclic Discrete Diffusion: A Novel Multi-Class Segmentation Refinement Technique
  9. NeurIPS 2026DC-ViT: Modulating Spatial and Channel Interactions for Multi-Channel Images
  10. NeurIPS 2026DDMS: Discriminative Distillation of Multi-view Foundational Features into Single-view Models
  11. NeurIPS 2026Decomposed Representations Mitigate the Alignment–Specificity Trade-off in Multi-Omics
  12. NeurIPS 2026Deconstructing Multi-Task Active Learning: The Paradox of Gradient Conflict and Orthogonal Decomposition
  13. NeurIPS 2026Delve into the Applicability of Advanced Optimizers for Multi-Task Learning
  14. NeurIPS 2026Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
  15. NeurIPS 2026Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
  16. NeurIPS 2026Driver Attention as Competitive Allocation: A Scene--Task-Aware Dual-Branch Framework
  17. NeurIPS 2026EEG Benchmarking Needs a Task Specification Layer: NeuroDoc for Rulebook-Guided, Executable Benchmark Construction
  18. NeurIPS 2026Efficient SAM 3 Adaptation for Multi-Class Semantic Segmentation via Dense Competitive Representations
  19. NeurIPS 2026Elastic Representations via Hyperbolic Geometry
  20. NeurIPS 2026Exponential Map Models as an Interpretable Framework for Generating Neural Spatial Representations
  21. NeurIPS 2026Focusable Monocular Depth Estimation
  22. NeurIPS 2026From Isolated feature to Orbits:\\Discovering Music Concepts via Multi-SAE Alignment
  23. NeurIPS 2026Frontier Task Synthesis Via Solution-Centric Evolution
  24. NeurIPS 2026Grouped Adaptive Head Mixing for Personalized Multi-Task Federated Reinforcement Learning
  25. NeurIPS 2026Harder the Task, Sparser the Representation: Sparsity as a Learning Signature of Capability in LLMs
  26. NeurIPS 2026How are linear representations learned? Exact solutions to the dynamics of abstraction
  27. NeurIPS 2026How Data Augmentation Shapes Neural Representations
  28. NeurIPS 2026HRIL: Isolating Multimodal Synergy via Higher-Order Dependence
  29. NeurIPS 2026Hydra: Towards Transferable Multi-Task Learning on Temporal Graphs
  30. NeurIPS 2026HyperSkill: Multi-Modal Skill Learning on the Unit Hypersphere
  31. NeurIPS 2026Individuals Matter: Improving Deep Multi-View Clustering via Explicit Single-View Enhancement
  32. NeurIPS 2026Insight-Driven Search: A Framework for Multi-objective Automated Heuristic Design with Large Language Models
  33. NeurIPS 2026InTAct: Interval-based Task Activation Consolidation for Continual Learning
  34. NeurIPS 2026Iterative ILP with Update-Size Control for Reducing Surrogate-Task Mismatch in Bit-Width Selection
  35. NeurIPS 2026Justitia: Fair and Efficient Scheduling of Task-parallel LLM Agents with Selective Pampering
  36. NeurIPS 2026Laplacian Heads Improve Transformers by Smoothing Token Representations
  37. NeurIPS 2026Learning Interpretable Switching Dynamics in Shared Neural-Behavioral Latent Space
  38. NeurIPS 2026Learning Task-Centric World Models from Visual Foundations
  39. NeurIPS 2026Learning What to Predict: Downstream-Guided Task Design for Continued Pretraining
  40. NeurIPS 2026LoRASpace: A Pool-Wide Shared Substrate for Static and Dynamic Multi-LoRA Composition
  41. NeurIPS 2026MAdam: Metric-Aware Multi-Objective Adam
  42. NeurIPS 2026MAGE: Towards Generalizable Multi-timescale EEG Representations
  43. NeurIPS 2026MaRiO: Multi-agent Collaborative Reasoning via Shared Observations in MLLMs
  44. NeurIPS 2026Market-Based Runtime Resource Allocation for LLM Multi-Agent Systems
  45. NeurIPS 2026Markov Metrical Task Systems
  46. NeurIPS 2026MC-H: Multi-Granularity Clustering with Hyperspherical Determinantal Point Process
  47. NeurIPS 2026MCAS: Signal-Processing-Based Multi-View Contrastive Learning for Acoustic Sensing
  48. NeurIPS 2026Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios
  49. NeurIPS 2026Mitigating Reward Hacking via Task Representations
  50. NeurIPS 2026MLLM Makes Strong Backbone for Multi-Modal Object Detection

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 查多任务学习在 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-learning"}

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学习论文？
共 1,181 篇，按年份分别是 2023 年 288 篇、2024 年 227 篇、2025 年 264 篇、2026 年 402 篇。
NeurIPS 2026 有多少篇多任务学习论文？
NeurIPS 2026 有 126 篇多任务学习论文，上一届是 101 篇。
ICLR 2026 有多少篇多任务学习论文？
ICLR 2026 有 57 篇多任务学习论文，上一届是 40 篇。
ICML 2026 有多少篇多任务学习论文？
ICML 2026 有 91 篇多任务学习论文，上一届是 47 篇。
CVPR 2026 有多少篇多任务学习论文？
CVPR 2026 有 128 篇多任务学习论文，上一届是 76 篇。
哪个会议的多任务学习论文最多？
NeurIPS，2023–2026 年共 399 篇。

「元学习与迁移」下的其他主题