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 10 / 24 页

  1. CVPR 2025Multi-modal Topology-embedded Graph Learning for Spatially Resolved Genes Prediction from Pathology Images with Prior Gene Similarity Information
  2. CVPR 2025Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation
  3. CVPR 2025MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction
  4. CVPR 2025MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D
  5. CVPR 2025One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion
  6. CVPR 2025PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches
  7. CVPR 2025PDFactor: Learning Tri-Perspective View Policy Diffusion Field for Multi-Task Robotic Manipulation
  8. CVPR 2025ProHOC: Probabilistic Hierarchical Out-of-Distribution Classification via Multi-Depth Networks
  9. CVPR 2025RANGE: Retrieval Augmented Neural Fields for Multi-Resolution Geo-Embeddings
  10. CVPR 2025ROLL: Robust Noisy Pseudo-label Learning for Multi-View Clustering with Noisy Correspondence
  11. CVPR 2025SINR: Sparsity Driven Compressed Implicit Neural Representations
  12. CVPR 2025SIR-DIFF: Sparse Image Sets Restoration with Multi-View Diffusion Model
  13. CVPR 2025SocialGesture: Delving into Multi-person Gesture Understanding
  14. CVPR 2025SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis
  15. CVPR 2025STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal Classification
  16. CVPR 2025TADFormer: Task-Adaptive Dynamic TransFormer for Efficient Multi-Task Learning
  17. CVPR 2025Task Singular Vectors: Reducing Task Interference in Model Merging
  18. CVPR 2025Task-Agnostic Guided Feature Expansion for Class-Incremental Learning
  19. CVPR 2025Test-Time Fine-Tuning of Image Compression Models for Multi-Task Adaptability
  20. CVPR 2025Theory-Inspired Deep Multi-View Multi-Label Learning with Incomplete Views and Noisy Labels
  21. CVPR 2025TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization
  22. CVPR 2025Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters
  23. CVPR 2025Towards Optimizing Large-Scale Multi-Graph Matching in Bioimaging
  24. CVPR 2025Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation
  25. CVPR 2025Understanding Multi-Task Activities from Single-Task Videos
  26. CVPR 2025VL2Lite: Task-Specific Knowledge Distillation from Large Vision-Language Models to Lightweight Networks
  27. CVPR 2025WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and Segmentation
  28. CVPR 2025Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos
  29. ICLR 2025Active Task Disambiguation with LLMs
  30. ICLR 2025Balanced Ranking with Relative Centrality: A multi-core periphery perspective
  31. ICLR 2025CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs
  32. ICLR 2025CREIMBO: Cross-Regional Ensemble Interactions in Multi-view Brain Observations
  33. ICLR 2025Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs
  34. ICLR 2025Denoising Task Difficulty-based Curriculum for Training Diffusion Models
  35. ICLR 2025DEPT: Decoupled Embeddings for Pre-training Language Models
  36. ICLR 2025Disentangling Representations through Multi-task Learning
  37. ICLR 2025Dynamic Modeling of Patients, Modalities and Tasks via Multi-modal Multi-task Mixture of Experts
  38. ICLR 2025Efficient Low-Bit Quantization with Adaptive Scales for Multi-Task Co-Training
  39. ICLR 2025Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic
  40. ICLR 2025GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning
  41. ICLR 2025Holographic Node Representations: Pre-training Task-Agnostic Node Embeddings
  42. ICLR 2025Learning Diagrams: A Graphical Language for Compositional Training Regimes
  43. ICLR 2025Learning Task Belief Similarity with Latent Dynamics for Meta-Reinforcement Learning
  44. ICLR 2025Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs
  45. ICLR 2025LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging
  46. ICLR 2025Many-Objective Multi-Solution Transport
  47. ICLR 2025MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation
  48. ICLR 2025Mastering Task Arithmetic: $\tau$Jp as a Key Indicator for Weight Disentanglement
  49. ICLR 2025Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning
  50. ICLR 2025Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace

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