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 171 篇，第 2 / 4 页

  1. ICLR 2026Scaling Multi-Task Bayesian Optimization with Large Language Models
  2. ICLR 2026SpectraLLM: Uncovering the Ability of LLMs for Molecule Structure Elucidation from Multi-Spectra
  3. ICLR 2026SwiftTS: A Swift Selection Framework for Time Series Pre-trained Models via Multi-task Meta-Learning
  4. ICLR 2026Task-Agnostic Amortized Multi-Objective Optimization
  5. ICLR 2026Toward Enhancing Representation Learning in Federated Multi-Task Settings
  6. ICLR 2026TyphoonMLA: A Mixed Naive-Absorb MLA Kernel For Shared Prefix
  7. ICLR 2026Wavelet Predictive Representations for Non-Stationary Reinforcement Learning
  8. ICLR 2025Active Task Disambiguation with LLMs
  9. ICLR 2025Balanced Ranking with Relative Centrality: A multi-core periphery perspective
  10. ICLR 2025CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs
  11. ICLR 2025CREIMBO: Cross-Regional Ensemble Interactions in Multi-view Brain Observations
  12. ICLR 2025Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs
  13. ICLR 2025Denoising Task Difficulty-based Curriculum for Training Diffusion Models
  14. ICLR 2025DEPT: Decoupled Embeddings for Pre-training Language Models
  15. ICLR 2025Disentangling Representations through Multi-task Learning
  16. ICLR 2025Dynamic Modeling of Patients, Modalities and Tasks via Multi-modal Multi-task Mixture of Experts
  17. ICLR 2025Efficient Low-Bit Quantization with Adaptive Scales for Multi-Task Co-Training
  18. ICLR 2025Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic
  19. ICLR 2025GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning
  20. ICLR 2025Holographic Node Representations: Pre-training Task-Agnostic Node Embeddings
  21. ICLR 2025Learning Diagrams: A Graphical Language for Compositional Training Regimes
  22. ICLR 2025Learning Task Belief Similarity with Latent Dynamics for Meta-Reinforcement Learning
  23. ICLR 2025Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs
  24. ICLR 2025LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging
  25. ICLR 2025Many-Objective Multi-Solution Transport
  26. ICLR 2025MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation
  27. ICLR 2025Mastering Task Arithmetic: $\tau$Jp as a Key Indicator for Weight Disentanglement
  28. ICLR 2025Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning
  29. ICLR 2025Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace
  30. ICLR 2025MTSAM: Multi-Task Fine-Tuning for Segment Anything Model
  31. ICLR 2025Multi-objective Differentiable Neural Architecture Search
  32. ICLR 2025Multi-Resolution Decomposable Diffusion Model for Non-Stationary Time Series Anomaly Detection
  33. ICLR 2025Multi-session, multi-task neural decoding from distinct cell-types and brain regions
  34. ICLR 2025Multi-Task Dense Predictions via Unleashing the Power of Diffusion
  35. ICLR 2025NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals
  36. ICLR 2025Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences
  37. ICLR 2025Perm: A Parametric Representation for Multi-Style 3D Hair Modeling
  38. ICLR 2025Rethinking Neural Multi-Objective Combinatorial Optimization via Neat Weight Embedding
  39. ICLR 2025REVISITING MULTI-PERMUTATION EQUIVARIANCE THROUGH THE LENS OF IRREDUCIBLE REPRESENTATIONS
  40. ICLR 2025Selective Task Group Updates for Multi-Task Optimization
  41. ICLR 2025SpaceGNN: Multi-Space Graph Neural Network for Node Anomaly Detection with Extremely Limited Labels
  42. ICLR 2025STAFF: Speculative Coreset Selection for Task-Specific Fine-tuning
  43. ICLR 2025Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning
  44. ICLR 2025Task Descriptors Help Transformers Learn Linear Models In-Context
  45. ICLR 2025Towards Optimal Multi-draft Speculative Decoding
  46. ICLR 2025When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
  47. ICLR 2025Which Tasks Should Be Compressed Together? A Causal Discovery Approach for Efficient Multi-Task Representation Compression
  48. ICLR 2024AdaMerging: Adaptive Model Merging for Multi-Task Learning
  49. ICLR 2024Augmenting Transformers with Recursively Composed Multi-grained Representations
  50. ICLR 2024Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost

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