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 14 / 24 页

  1. NeurIPS 2025Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs
  2. NeurIPS 2025Scalable Cross-View Sample Alignment for Multi-View Clustering with View Structure Similarity
  3. NeurIPS 2025Scaling Image Geo-Localization to Continent Level
  4. NeurIPS 2025SIFusion: A Unified Fusion Framework for Multi-granularity Arctic Sea Ice Forecasting
  5. NeurIPS 2025Single GPU Task Adaptation of Pathology Foundation Models for Whole Slide Image Analysis
  6. NeurIPS 2025SMARTraj$^2$: A Stable Multi-City Adaptive Method for Multi-View Spatio-Temporal Trajectory Representation Learning
  7. NeurIPS 2025Soft Task-Aware Routing of Experts for Equivariant Representation Learning
  8. NeurIPS 2025SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D Tracking
  9. NeurIPS 2025Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain
  10. NeurIPS 2025Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations
  11. NeurIPS 2025Theory-Driven Label-Specific Representation for Incomplete Multi-View Multi-Label Learning
  12. NeurIPS 2025Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration
  13. NeurIPS 2025TS-MOF: Two-Stage Multi-Objective Fine-tuning for Long-Tailed Recognition
  14. NeurIPS 2025Unbiased Prototype Consistency Learning for Multi-Modal and Multi-Task Object Re-Identification
  15. NeurIPS 2025VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models
  16. NeurIPS 2025Where Graph Meets Heterogeneity: Multi-View Collaborative Graph Experts
  17. CVPR 20242S-UDF: A Novel Two-stage UDF Learning Method for Robust Non-watertight Model Reconstruction from Multi-view Images
  18. CVPR 2024A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives
  19. CVPR 2024Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes
  20. CVPR 2024AssistGUI: Task-Oriented PC Graphical User Interface Automation
  21. CVPR 2024Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing
  22. CVPR 2024Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining
  23. CVPR 2024Binding Touch to Everything: Learning Unified Multimodal Tactile Representations
  24. CVPR 2024Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations
  25. CVPR 2024Category-Level Multi-Part Multi-Joint 3D Shape Assembly
  26. CVPR 2024Class Incremental Learning with Multi-Teacher Distillation
  27. CVPR 2024CLIP-BEVFormer: Enhancing Multi-View Image-Based BEV Detector with Ground Truth Flow
  28. CVPR 2024Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment
  29. CVPR 2024CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing
  30. CVPR 2024Differentiable Information Bottleneck for Deterministic Multi-view Clustering
  31. CVPR 2024DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data
  32. CVPR 2024DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning
  33. CVPR 2024Dual DETRs for Multi-Label Temporal Action Detection
  34. CVPR 2024EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI
  35. CVPR 2024Event-based Visible and Infrared Fusion via Multi-task Collaboration
  36. CVPR 2024FedHCA2: Towards Hetero-Client Federated Multi-Task Learning
  37. CVPR 2024Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture
  38. CVPR 2024GALA: Generating Animatable Layered Assets from a Single Scan
  39. CVPR 2024Generative Multi-modal Models are Good Class Incremental Learners
  40. CVPR 2024GeoAuxNet: Towards Universal 3D Representation Learning for Multi-sensor Point Clouds
  41. CVPR 2024Going Beyond Multi-Task Dense Prediction with Synergy Embedding Models
  42. CVPR 2024GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo
  43. CVPR 2024Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation
  44. CVPR 2024Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models
  45. CVPR 2024Improving Bird's Eye View Semantic Segmentation by Task Decomposition
  46. CVPR 2024Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions
  47. CVPR 2024Joint-Task Regularization for Partially Labeled Multi-Task Learning
  48. CVPR 2024Learn from View Correlation: An Anchor Enhancement Strategy for Multi-view Clustering
  49. CVPR 2024M&M VTO: Multi-Garment Virtual Try-On and Editing
  50. CVPR 2024Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification

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