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 363 篇，第 4 / 8 页

  1. CVPR 2025Enhanced then Progressive Fusion with View Graph for Multi-View Clustering
  2. CVPR 2025Focusing on Tracks for Online Multi-Object Tracking
  3. CVPR 2025Free Lunch Enhancements for Multi-modal Crowd Counting
  4. CVPR 2025GeoMM: On Geodesic Perspective for Multi-modal Learning
  5. CVPR 2025GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery
  6. CVPR 2025Hierarchical Knowledge Prompt Tuning for Multi-task Test-Time Adaptation
  7. CVPR 2025Identifying and Mitigating Spurious Correlation in Multi-Task Learning
  8. CVPR 2025IMFine: 3D Inpainting via Geometry-guided Multi-view Refinement
  9. CVPR 2025Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning
  10. CVPR 2025Joint Scheduling of Causal Prompts and Tasks for Multi-Task Learning
  11. CVPR 2025KMD: Koopman Multi-modality Decomposition for Generalized Brain Tumor Segmentation under Incomplete Modalities
  12. CVPR 2025Large-scale Multi-view Tensor Clustering with Implicit Linear Kernels
  13. CVPR 2025Learning from Synchronization: Self-Supervised Uncalibrated Multi-View Person Association in Challenging Scenes
  14. CVPR 2025Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels
  15. CVPR 2025Less is More: Efficient Model Merging with Binary Task Switch
  16. CVPR 2025MangaNinja: Line Art Colorization with Precise Reference Following
  17. CVPR 2025MIRE: Matched Implicit Neural Representations
  18. CVPR 2025MLVU: Benchmarking Multi-task Long Video Understanding
  19. CVPR 2025MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling
  20. CVPR 2025MMRL: Multi-Modal Representation Learning for Vision-Language Models
  21. CVPR 2025MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception
  22. CVPR 2025MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes
  23. CVPR 2025Mr. DETR: Instructive Multi-Route Training for Detection Transformers
  24. CVPR 2025Multi-Group Proportional Representations for Text-to-Image Models
  25. CVPR 2025Multi-Modal Contrastive Masked Autoencoders: A Two-Stage Progressive Pre-training Approach for RGBD Datasets
  26. CVPR 2025Multi-Modal Synergistic Implicit Image Enhancement for Efficient Optical Flow Estimation
  27. CVPR 2025Multi-modal Topology-embedded Graph Learning for Spatially Resolved Genes Prediction from Pathology Images with Prior Gene Similarity Information
  28. CVPR 2025Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation
  29. CVPR 2025MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction
  30. CVPR 2025MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D
  31. CVPR 2025One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion
  32. CVPR 2025PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches
  33. CVPR 2025PDFactor: Learning Tri-Perspective View Policy Diffusion Field for Multi-Task Robotic Manipulation
  34. CVPR 2025ProHOC: Probabilistic Hierarchical Out-of-Distribution Classification via Multi-Depth Networks
  35. CVPR 2025RANGE: Retrieval Augmented Neural Fields for Multi-Resolution Geo-Embeddings
  36. CVPR 2025ROLL: Robust Noisy Pseudo-label Learning for Multi-View Clustering with Noisy Correspondence
  37. CVPR 2025SINR: Sparsity Driven Compressed Implicit Neural Representations
  38. CVPR 2025SIR-DIFF: Sparse Image Sets Restoration with Multi-View Diffusion Model
  39. CVPR 2025SocialGesture: Delving into Multi-person Gesture Understanding
  40. CVPR 2025SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis
  41. CVPR 2025STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal Classification
  42. CVPR 2025TADFormer: Task-Adaptive Dynamic TransFormer for Efficient Multi-Task Learning
  43. CVPR 2025Task Singular Vectors: Reducing Task Interference in Model Merging
  44. CVPR 2025Task-Agnostic Guided Feature Expansion for Class-Incremental Learning
  45. CVPR 2025Test-Time Fine-Tuning of Image Compression Models for Multi-Task Adaptability
  46. CVPR 2025Theory-Inspired Deep Multi-View Multi-Label Learning with Incomplete Views and Noisy Labels
  47. CVPR 2025TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization
  48. CVPR 2025Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters
  49. CVPR 2025Towards Optimizing Large-Scale Multi-Graph Matching in Bioimaging
  50. CVPR 2025Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation

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