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 402 篇，第 6 / 9 页

  1. ICML 2026Orthogonal Model Merging
  2. ICML 2026Personalized Additive Modeling for Multi-level Federated Learning
  3. ICML 2026Post-Hoc Merging is Not Enough: Many-Shot Model Merging with Loss-Gap Balancing
  4. ICML 2026Predicting evolutionary rate as a pretraining task improves genome language model representations
  5. ICML 2026Probabilistic Performance Guarantees for Multi-Task Reinforcement Learning
  6. ICML 2026Problem Distributions as Tasks: Repurposing Meta Learning for Generative Combinatorial Optimization towards Multi-task Pretraining and Adaptation
  7. ICML 2026Rethinking Human Intent-to-CAD: Parametric CAD Model Generation via Cooperative Multi-Task Alignment and Spatial-Aware Reinforcement Learning
  8. ICML 2026Saliency-Aware Model Merging
  9. ICML 2026Shared Lexical Task Representations Explain Behavioral Variability In LLMs
  10. ICML 2026Sketch-Based Low-Rank Model Merging with Shared Circulant Transforms
  11. ICML 2026Structured Expert Routing with Multi-View Task Priors for Offline Meta-Reinforcement Learning
  12. ICML 2026Structured Multi-modal Graph Disentanglement for Psychiatric Diagnosis
  13. ICML 2026SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation
  14. ICML 2026T-GINEE: A Tensor-Based Multi-Graph Representation Learning
  15. ICML 2026TACTIC: Task-Aware Sparse Coordination Graphs for Multi-Task Multi-agent Reinforcement Learning
  16. ICML 2026Task-Aware Exploration via a Predictive Bisimulation Metric
  17. ICML 2026Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning
  18. ICML 2026The Geometry of Updates: Fisher Alignment at Vocabulary Scale
  19. ICML 2026TimeMRA: LLM-Empowered Time Series Forecasting via Multi-Scale Retrieval-Augmented Representations
  20. ICML 2026Transformers learn factored representations
  21. ICML 2026Transporting Task Vectors across Different Architectures without Training
  22. ICML 2026Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining
  23. ICML 2026WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving
  24. ICML 2026Weaving in the Clouds: Achieving Synergistic Collaboration among LLM Agents via Federated Learning
  25. ICML 2026What Linear Probes Miss: Multi-View Probing for Weight-Space Learning
  26. ICML 2026When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging
  27. NeurIPS 2026A Black-Box Reduction from Regret to Multi-Level Coverage
  28. NeurIPS 2026A Mahalanobis Margin \texorpdfstring{$\gamma_{\min}$}{gamma\_min} Bound on Task Confusion in Pretrained Class-Incremental Learning: From Infeasibility to Exponential Attenuation
  29. NeurIPS 2026A Scalable Multi-Task Model for Virtual Sensors
  30. NeurIPS 2026A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning
  31. NeurIPS 2026Adaptive LLM Routing for Multi-Turn Conversations with Continuously Evolving User Queries
  32. NeurIPS 2026Adaptive Multi-view Graph Contrastive Learning via Fractional Continuous Dynamics
  33. NeurIPS 2026AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace
  34. NeurIPS 2026ArcMark: Distortion-Free Multi-Byte LLM Watermark via Optimal Transport
  35. NeurIPS 2026ASTOR: Multi-Task Code Reinforcement Learning via Utility-Driven Coordination
  36. NeurIPS 2026Attention Is More Than You Need: Spectral Redundancy in Multi-Head Routing
  37. NeurIPS 2026BACE: Behavior-Adaptive Connectivity Estimation from Multi-Region Neural Recordings
  38. NeurIPS 2026Balanced Multi-Task Learning from an Optimality-Gap Perspective
  39. NeurIPS 2026Bandits via Additive Quantized Representations
  40. NeurIPS 2026Benchmarking Open-Ended Multi-Agent Coordination in Language Agents
  41. NeurIPS 2026BESS-Bench: Benchmarking Spectral Representations for Be-Star Variability
  42. NeurIPS 2026Beyond FLOPs: Train-Full, Deploy-Partial Multi-Exit Inference via Selective Lightweight IC Ensemble
  43. NeurIPS 2026Beyond Outcome: Trajectory-Driven Prompt Optimization via Multi-Dimensional Rewards
  44. NeurIPS 2026Beyond Semantic Alignment: Geometric Incomparability in Multi-Oracle Soft Fusion
  45. NeurIPS 2026Bilevel Optimization of Synthetic Trajectories for Multi-Turn LLM Fine-Tuning
  46. NeurIPS 2026BitMTP: When Multi-Token Prediction Meets Low-Bit Large Language Models
  47. NeurIPS 2026BrainCoT: A Multi-Task Zero-Shot Brain Signal Foundation Model with Neurometric-Anchored Chain-of-Thought Reasoning
  48. NeurIPS 2026C3P: Contrastive promoter-protein pretraining yields representations capturing bacterial gene regulation
  49. NeurIPS 2026Can Metadata Fix the Gauge? Calibration Turns Sparse Multi-Source Learning from Sparse PCA into Sparse Mean Recovery
  50. NeurIPS 2026Causal Multi-Task Demand Learning

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