Paper Detail

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

Shih-Wen Liu, Yen-Chang Chen, Wei-Ta Chu, Fu-En Yang, Yu-Chiang Frank Wang

arxiv Score 6.8

Published 2026-03-22 · First seen 2026-03-27

General AI

Abstract

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 \textbf{Free Sinewich}, a parameter-efficient multi-task learning framework that enables near-zero-cost weight modulation via frequency switching (\textbf{Free}). Specifically, a \textbf{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: \href{https://casperliuliuliu.github.io/projects/Free-Sinewich/}{https://casperliuliuliu.github.io/projects/Free-Sinewich}.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{liu2026frequency,
  title = {Frequency Switching Mechanism for Parameter-E!cient Multi-Task Learning},
  author = {Shih-Wen Liu and Yen-Chang Chen and Wei-Ta Chu and Fu-En Yang and Yu-Chiang Frank Wang},
  year = {2026},
  abstract = {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 \textbackslash{}textbf\{Free Sinewich\}, a parameter-efficient multi-task learning framework that enables near-zero-cost weight modulation via frequency switching (\textbackslash{}textbf\{Free\}). Specifically, a \textbackslash{}textbf\{Sine-AWB (Sinewich)\} layer combines low-rank factors and convolutional priors into a single k},
  url = {https://arxiv.org/abs/2603.21111},
  keywords = {cs.CV, cs.LG},
  eprint = {2603.21111},
  archiveprefix = {arXiv},
}

Metadata

{}