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}.

翻译：多任务学习（MTL）旨在使单一模型高效解决多个任务，然而当前的参数高效微调（PEFT）方法仍主要局限于单任务适应。我们提出**Free Sinewich**，一种参数高效的多任务学习框架，通过频率切换（**Free**）实现近乎零成本的权重调制。具体而言，**Sine-AWB（Sinewich）**层将低秩因子与卷积先验融合为单一核，随后通过正弦变换逐元素调制生成任务专用权重。引入轻量级Clock Net以产生有界频率，在训练过程中稳定该调制过程。理论分析表明，正弦调制增强了低秩适配器的秩，而频率分离则去除了不同任务权重间的相关性。在密集预测基准测试中，Free Sinewich实现了性能-效率权衡的最优结果（例如，相较于单任务微调提升高达+5.39%，且仅需6.53M可训练参数），提供了一种基于频率参数共享的紧凑且可扩展范式。项目页面：\href{https://casperliuliuliu.github.io/projects/Free-Sinewich/}{https://casperliuliuliu.github.io/projects/Free-Sinewich}。