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 8 / 9 页

  1. NeurIPS 2026MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing
  2. NeurIPS 2026Multi-agent Collaboration with State Management
  3. NeurIPS 2026Multi-Agent Coordination via Support-Preserving Distillation
  4. NeurIPS 2026Multi-Constrained Randomized Smoothing Certificates
  5. NeurIPS 2026Multi-Environment POMDPs with Finite-Horizon Objectives
  6. NeurIPS 2026Multi-Level Alignment Framework for Long-Term Olfactory Neural Decoding
  7. NeurIPS 2026Multi-Part Object Representations via Graph Structures and Co-Part Discovery
  8. NeurIPS 2026Multi-Turn RL Makes Small Language Model Competitive for Optimization Modeling
  9. NeurIPS 2026MUSS: A Multi-scale and Sequence-based Model for Single-cell Gene Regulation
  10. NeurIPS 2026MvFFN: Multi-view Floor-Plan Feed-Forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction
  11. NeurIPS 2026Narrowing the Collaboration Gap, Probably
  12. NeurIPS 2026Near-Optimal Learning in Parametric Bandits with Action-Dependent Coarsened Feedback
  13. NeurIPS 2026Noise-Level KL Rates for Multi-Marginal Schrödinger Bridge Surrogates
  14. NeurIPS 2026OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
  15. NeurIPS 2026ORCA: Orthogonal Residual Consensus Alignment for Multi-View Clustering
  16. NeurIPS 2026OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism
  17. NeurIPS 2026Permutation Sensitivity in t-SVD-based Multi-view Clustering
  18. NeurIPS 2026PGSB: Pretrained-Guided Shared Basis for LoRA Model Merging
  19. NeurIPS 2026Physical AI Smart Spaces: A Large-Scale Benchmark for Multi-Camera 3D Perception in Smart Spaces
  20. NeurIPS 2026Platonic Task Arithmetic
  21. NeurIPS 2026Position: Fair Representations Cannot Hold What They Promise
  22. NeurIPS 2026Position: Lottery Tickets Do Not Explain Overparameterization. How About Escape Dimensions?
  23. NeurIPS 2026ProbMedTOD: A Bayesian Network Guided Task-Oriented Dialogue System for Patient History Taking
  24. NeurIPS 2026RAMA: Resistance-Aware Multi-Hop Aggregation Graph Representation Learning for Robust Ethereum Account Classification
  25. NeurIPS 2026Releasing Anchors from Cross-View Correspondence: Probabilistic Multi-View Anchor Graph Clustering
  26. NeurIPS 2026ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models
  27. NeurIPS 2026S²MoE: Shared-Subspace Mixture of Sparse Experts
  28. NeurIPS 2026SCION: Scene Composition via Instanced Neural Primitives
  29. NeurIPS 2026SelfGuard: Self-Supervised Deviation Modeling for Multi-Modal Jailbreak Detection
  30. NeurIPS 2026Sequence-to-Sequence Modeling with Camera-Induced Priors for Multi-View Stereo
  31. NeurIPS 2026Serialization Tax in Shared-Latent Exchangeable Decisions
  32. NeurIPS 2026SMOG: Scalable Meta-Learning for Multi-Objective Bayesian Optimization
  33. NeurIPS 2026SpanFormer: Multi-Level Adaptive Sparsity for Object Detection in High-Resolution Wide Shots
  34. NeurIPS 2026SpecBridge: Learning Natural-Language Formalization Plans for the Formal Specification Synthesis Task
  35. NeurIPS 2026SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents
  36. NeurIPS 2026Spectral Alignment in Forward–Backward Representations via Temporal Abstraction
  37. NeurIPS 2026Spectral Insights from the Unconstrained Feature Model for Neural Multi-Output Regression
  38. NeurIPS 2026Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation
  39. NeurIPS 2026Structurally Separated DAG Learning with Multi-Scale Normalized Closure
  40. NeurIPS 2026Sustainability in the Loop: AI Model Development Should Be Multi-Objective
  41. NeurIPS 2026SyncLight: Single-Edit Multi-View Relighting
  42. NeurIPS 2026TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability
  43. NeurIPS 2026The Alignment Illusion in Multimodal Large Language Models
  44. NeurIPS 2026The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size
  45. NeurIPS 2026TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing
  46. NeurIPS 2026TraceGuard: Defending Multi-Turn Jailbreak Attacks via Prompt-Response Risk Signal Tracking
  47. NeurIPS 2026UniReFP: Robust Unified Fingerprinting for Vision Models against Cross-Task Repurposing Attacks
  48. NeurIPS 2026ViewSAM: Learning View-aware Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking
  49. NeurIPS 2026Virtual Task Prompting for Multi-Task Scene Understanding
  50. NeurIPS 2026When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction

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