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 15 / 24 页

  1. CVPR 2024Mask4Align: Aligned Entity Prompting with Color Masks for Multi-Entity Localization Problems
  2. CVPR 2024Masked AutoDecoder is Effective Multi-Task Vision Generalist
  3. CVPR 2024MMA: Multi-Modal Adapter for Vision-Language Models
  4. CVPR 2024MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models
  5. CVPR 2024Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention
  6. CVPR 2024MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception
  7. CVPR 2024mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration
  8. CVPR 2024MTLoRA: Low-Rank Adaptation Approach for Efficient Multi-Task Learning
  9. CVPR 2024MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark
  10. CVPR 2024Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer
  11. CVPR 2024Multi-modal Learning for Geospatial Vegetation Forecasting
  12. CVPR 2024Multi-Scale Video Anomaly Detection by Multi-Grained Spatio-Temporal Representation Learning
  13. CVPR 2024Multi-Space Alignments Towards Universal LiDAR Segmentation
  14. CVPR 2024MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
  15. CVPR 2024MVCPS-NeuS: Multi-view Constrained Photometric Stereo for Neural Surface Reconstruction
  16. CVPR 2024NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis
  17. CVPR 2024OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion
  18. CVPR 2024Person-in-WiFi 3D: End-to-End Multi-Person 3D Pose Estimation with Wi-Fi
  19. CVPR 2024Prompt Highlighter: Interactive Control for Multi-Modal LLMs
  20. CVPR 2024Quantifying Task Priority for Multi-Task Optimization
  21. CVPR 2024Region-Based Representations Revisited
  22. CVPR 2024Rethinking Multi-view Representation Learning via Distilled Disentangling
  23. CVPR 2024Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery
  24. CVPR 2024Sharingan: A Transformer Architecture for Multi-Person Gaze Following
  25. CVPR 2024SketchINR: A First Look into Sketches as Implicit Neural Representations
  26. CVPR 2024SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution
  27. CVPR 2024SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery
  28. CVPR 2024StreamingFlow: Streaming Occupancy Forecasting with Asynchronous Multi-modal Data Streams via Neural Ordinary Differential Equation
  29. CVPR 2024TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding
  30. CVPR 2024Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning
  31. CVPR 2024Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations
  32. CVPR 2024Task-Conditioned Adaptation of Visual Features in Multi-Task Policy Learning
  33. CVPR 2024Task-Customized Mixture of Adapters for General Image Fusion
  34. CVPR 2024Task-Driven Wavelets using Constrained Empirical Risk Minimization
  35. CVPR 2024Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships
  36. CVPR 2024Towards Calibrated Multi-label Deep Neural Networks
  37. CVPR 2024Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training
  38. CVPR 2024Towards Progressive Multi-Frequency Representation for Image Warping
  39. CVPR 2024Training-Free Pretrained Model Merging
  40. CVPR 2024TULIP: Multi-camera 3D Precision Assessment of Parkinson's Disease
  41. CVPR 2024Unsupervised Gaze Representation Learning from Multi-view Face Images
  42. CVPR 2024Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval
  43. CVPR 2024YolOOD: Utilizing Object Detection Concepts for Multi-Label Out-of-Distribution Detection
  44. ICLR 2024AdaMerging: Adaptive Model Merging for Multi-Task Learning
  45. ICLR 2024Augmenting Transformers with Recursively Composed Multi-grained Representations
  46. ICLR 2024Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost
  47. ICLR 2024Class Incremental Learning via Likelihood Ratio Based Task Prediction
  48. ICLR 2024CLIP-MUSED: CLIP-Guided Multi-Subject Visual Neural Information Semantic Decoding
  49. ICLR 2024Combinatorial Bandits for Maximum Value Reward Function under Value-Index Feedback
  50. ICLR 2024Controlling Vision-Language Models for Multi-Task Image Restoration

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