mlsanityData to 7 Oct 2026

Frequency Switching Mechanism for Parameter-E!cient Multi-Task Learning

arXiv 2603.21111 ↗First posted 22 Mar 2026cs.CV cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Multi-task learning (MTL) aims to enable a single model to solve multiple tasks efficiently; however, current parameter-efficient fine-tuning (PEFT) methods remain largely limited to single-task adaptation. We introduce Free Sinewich, a parameter-efficient multi-task learning framework that enables near-zero-cost weight modulation via frequency switching (Free). Specifically, a Sine-AWB (Sinewich) layer combines low-rank factors and convolutional priors into a single kernel, which is then modulated elementwise by a sinusoidal transformation to produce task-specialized weights. A lightweight Clock Net is introduced to produce bounded frequencies that stabilize this modulation during training. Theoretically, sine modulation enhances the rank of low-rank adapters, while frequency separation decorrelates the weights of different tasks. On dense prediction benchmarks, Free Sinewich achieves state-of-the-art performance-efficiency trade-offs (e.g., up to +5.39% improvement over single-task fine-tuning with only 6.53M trainable parameters), offering a compact and scalable paradigm based on frequency-based parameter sharing. Project page: hrefhttps://casperliuliuliu.github.io/projects/Free-Sinewich/https://casperliuliuliu.github.io/projects/Free-Sinewich.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 22 Mar 2026.

Builds on

31 of 45 references.

References · 31

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  6. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  7. 2022Visual Prompt Tuningcited by 1,674
  8. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  9. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,234
  10. 2020Gradient Surgery for Multi-Task Learningcited by 1,210
  11. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 886
  12. 2021Towards a Unified View of Parameter-Efficient Transfer Learningcited by 863
19 more
  1. 2017A Survey on Multi-Task Learningcited by 838
  2. 2024DoRA: Weight-Decomposed Low-Rank Adaptationcited by 740
  3. 2024Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Surveycited by 641
  4. 2018Do Better ImageNet Models Transfer Better?cited by 560
  5. 2021Compacter: Efficient Low-Rank Hypercomplex Adapter Layerscited by 458
  6. 2021VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Taskscited by 319
  7. 2021Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworkscited by 278
  8. 2022Multi-Task Learning as a Bargaining Gamecited by 209
  9. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  10. 2024Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Modelcited by 67
  11. 2022Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Taskscited by 52
  12. 2024MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learningcited by 44
  13. 2024Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologiescited by 44
  14. 2023A survey of the Vision Transformers and their CNN-Transformer based Variantscited by 33
  15. 2024Efficient Learning With Sine-Activated Low-rank Matricescited by 22
  16. 2024DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Datacited by 18
  17. 2025PEFT A2Z: Parameter-Efficient Fine-Tuning Survey for Large Language and Vision Modelscited by 16
  18. 2025DiTASK: Multi-Task Fine-Tuning with Diffeomorphic Transformationscited by 7
  19. 2025TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026DeCo: Efficient Decouple-to-Couple Learning for Multi-Task Visual Groundingcited by 0