mlsanityData to 14 Oct 2026

Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation

arXiv 2509.19602 ↗First posted 23 Sep 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Parameter-efficient fine-tuning methods have emerged as a promising solution for adapting pre-trained models to various downstream tasks. While these methods perform well in single-task learning, extending them to multi-task learning exacerbates common issues, such as task interference and negative transfer, due to the limited number of trainable parameters. To address these challenges, we introduce progressive task-specific multi-task adaptation, a novel parameter-efficient approach for multi-task learning. Our approach introduces adapter modules that are shared in early layers and become increasingly task-specific in later layers. Additionally, we propose a gradient-based approach for computing task similarity and use this measure to allocate similar tasks to the shared adapter modules. To evaluate our approach, we adapt Swin and Pyramid Vision Transformers on PASCAL and NYUD-v2. On both datasets, our approach outperforms prior parameter-efficient multi-task methods while using fewer trainable parameters.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 47 of its 66 references that are in the map. First posted on arXiv 23 Sep 2025.

Builds on

47 of 66 references.

References · 47

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  6. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  7. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  8. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  9. 2022Visual Prompt Tuningcited by 1,681
  10. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  11. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  12. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
35 more
  1. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,245
  2. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 834
  3. 2020AdapterFusion: Non-Destructive Task Composition for Transfer Learningcited by 788
  4. 2024DoRA: Weight-Decomposed Low-Rank Adaptationcited by 758
  5. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 719
  6. 2023LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Modelcited by 602
  7. 2022Vision Transformer Adapter for Dense Predictionscited by 565
  8. 2020AdapterHub: A Framework for Adapting Transformerscited by 444
  9. 2024LoRA+: Efficient Low Rank Adaptation of Large Modelscited by 377
  10. 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 375
  11. 2023LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Modelscited by 324
  12. 2021Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworkscited by 284
  13. 2014Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Partscited by 232
  14. 2018PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsingcited by 224
  15. 2021Efficiently Identifying Task Groupings for Multi-Task Learningcited by 222
  16. 2021Training Neural Networks with Fixed Sparse Maskscited by 214
  17. 2023Sequential Modeling Enables Scalable Learning for Large Vision Modelscited by 212
  18. 2019Task2Vec: Task Embedding for Meta-Learningcited by 205
  19. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  20. 2019Attentive Single-Tasking of Multiple Taskscited by 148
  21. 2022AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuningcited by 137
  22. 2020Learning to Branch for Multi-Task Learningcited by 115
  23. 2016Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classificationcited by 93
  24. 2022InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understandingcited by 89
  25. 2019Branched Multi-Task Networks: Deciding What Layers To Sharecited by 76
  26. 2023Independent Component Alignment for Multi-Task Learningcited by 70
  27. 2024Multi-Task Dense Prediction via Mixture of Low-Rank Expertscited by 58
  28. 2022Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Taskscited by 52
  29. 2020Automated Search for Resource-Efficient Branched Multi-Task Networkscited by 51
  30. 2024Fair Resource Allocation in Multi-Task Learningcited by 35
  31. 2024LoRA Dropout as a Sparsity Regularizer for Overfitting Controlcited by 35
  32. 2024Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Erascited by 26
  33. 2024MTL-LoRA: Low-Rank Adaptation for Multi-Task Learningcited by 17
  34. 2024PEMT: Multi-Task Correlation Guided Mixture-of-Experts Enables Parameter-Efficient Transfer Learningcited by 7
  35. 2025TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learningcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Parameter-efficient Quantum Multi-task Learningcited by 0