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 3 / 24 页

  1. CVPR 2026Rethinking Position Embedding as a Context Controller for Multi-Reference and
  2. CVPR 2026Scalable Multi-View Subspace Clustering with Tensorized Anchor Guidance
  3. CVPR 2026ShreddingNet Coarse-to-Fine Restoration for Multi-Source Shredded Manuscripts
  4. CVPR 2026SigLino Efficient Multi-Teacher Distillation for Agglomerative Vision Foundation Models
  5. CVPR 2026Skullptor High Fidelity 3D Head Reconstruction in Seconds with Multi-View
  6. CVPR 2026Sparse Task Vector Mixup with Hypernetworks for Efficient Knowledge Transfer
  7. CVPR 2026SPE-MVS Spatial Position Encoding Enhanced Multi-View Stereo with Monocular Depth
  8. CVPR 2026Spectrally Distilled Representations Aligned with Instruction-Augmented LLMs for Satellite Imagery
  9. CVPR 2026StableMTL Repurposing Latent Diffusion Models for Multi-Task Learning from Partially
  10. CVPR 2026Stay in your Lane Role Specific Queries with Overlap Suppression
  11. CVPR 2026Task-Aware Image Signal Processor for Advanced Visual Perception
  12. CVPR 2026Task-Driven Implicit Representations for Automated Design of LiDAR Systems
  13. CVPR 2026TaskIT Memory-Efficient Fine-Tuning of Multi-LoRA LLMs via Cross-Task Importance Transfer
  14. CVPR 2026TempR1 Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement
  15. CVPR 2026Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing
  16. CVPR 2026Test-Time Multi-Prompt Adaptation for Open-Vocabulary Remote Sensing Image Segmentation
  17. CVPR 2026Toward Generalizable Whole Brain Representations with High-Resolution Light-Sheet Data
  18. CVPR 2026Tri-Subspaces Disentanglement for Multimodal Sentiment Analysis
  19. CVPR 2026TSTM Temporal Segmentation for Task-relevant Mask in Visual Reinforcement Learning
  20. CVPR 2026Unique Lives Shared World Learning from Single-Life Videos
  21. CVPR 2026UnityVideo Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation
  22. CVPR 2026UniVerse A Unified Modulation Framework for Segmentation-Free Disentangled Multi-Concept Personalization
  23. CVPR 2026URScenes A Multi-scenario Dataset for Unstructured Road Environments
  24. CVPR 2026V2-SAM Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence
  25. CVPR 2026Virtual Immunohistochemistry Staining with Dual-Aligned Multi-Task Feature Guidance
  26. CVPR 2026Wan-Weaver Interleaved Multi-modal Generation via Decoupled Training
  27. CVPR 2026WeatherCity Urban Scene Reconstruction with Controllable Multi-Weather Transformation
  28. CVPR 2026WHU-MARS A Multispectral Aerial-Ground Benchmark Towards Any-Scenario Person Re-Identification
  29. ICLR 2026Adaptive Test-Time Training for Predicting Need for Invasive Mechanical Ventilation in Multi-Center Cohorts
  30. ICLR 2026Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?
  31. ICLR 2026Beyond Hearing: Learning Task-agnostic ExG Representations from Earphones via Physiology-informed Tokenization
  32. ICLR 2026Beyond Uniformity: Regularizing Implicit Neural Representations through a Lipschitz Lens
  33. ICLR 2026Calibrated Information Bottleneck for Trusted Multi-modal Clustering
  34. ICLR 2026CatalystBench: A Comprehensive Multi-Task Benchmark for Advancing Language Models in Catalysis Science
  35. ICLR 2026Chain-of-Context Learning: Dynamic Constraint Understanding for Multi-Task VRPs
  36. ICLR 2026CircuitNet 3.0: A Multi-Modal Dataset with Task-Oriented Augmentation for AI-Driven Circuit Design
  37. ICLR 2026Combination-of-Experts with Knowledge Sharing for Cross-Task Vehicle Routing Problems
  38. ICLR 2026Coupled Transformer Autoencoder for Disentangling Multi-Region Neural Latent Dynamics
  39. ICLR 2026Cross-Domain Lossy Compression via Rate- and Classification-Constrained Optimal Transport
  40. ICLR 2026Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature
  41. ICLR 2026DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
  42. ICLR 2026Domain Expansion: A Latent Space Construction Framework for Multi-Task Learning
  43. ICLR 2026Dual Goal Representations
  44. ICLR 2026Dual-Branch Representations with Dynamic Gated Fusion and Triple-Granularity Alignment for Deep Multi-View Clustering
  45. ICLR 2026Emergent Coordination in Multi-Agent Language Models
  46. ICLR 2026Enhanced Continual Learning of Vision-Language Models with Model Fusion
  47. ICLR 2026Ensemble Prediction of Task Affinity for Efficient Multi-Task Learning
  48. ICLR 2026EquAct: An SE(3)-Equivariant Multi-Task Transformer for 3D Robotic Manipulation
  49. ICLR 2026From Embedding to Control: Representations for Stochastic Multi-Object Systems
  50. ICLR 2026From Gradient Volume to Shapley Fairness: Towards Fair Multi-Task Learning

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