{"ID":5346735,"CreatedAt":"2026-06-30T04:09:55.830587294Z","UpdatedAt":"2026-07-02T14:28:49.359749133Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.30370","arxiv_id":"2606.30370","title":"MUSE: Unlocking Timestep as Native Task Steering for One-Step Dense Prediction","abstract":"Monocular dense prediction has recently seen remarkable success by repurposing pre-trained diffusion models. This opens a promising yet challenging avenue for more efficient multi-task learning paradigm. However, existing multi-task diffusion methods often introduce parameter-heavy adapters, experts, or learnable task tokens, leading to computational redundancy. In this paper, we reveal an inherent mechanism within one-step diffusion models: the native, fixed sinusoidal timestep embedding can be repurposed as an endogenous task steering signal. Based on this discovery, we propose Multi-task Unified eStimation via timestep Embedding (MUSE), a parameter-free, single-model multi-tasking approach for dense prediction. We interpret this mechanism via Manifold Decoupling, where discrete, fixed timestep values deterministically steer the generation process towards decoupled, task-specific manifolds in the latent space. Extensive experiments across 10 datasets demonstrate that MUSE achieves highly competitive performance on both monocular depth and normal estimation, and its efficacy generalizes across U-Net and DiT architectures. Our work offers a concise and efficient path toward generalist vision models by simply unlocking the latent potential of existing generation infrastructure.","short_abstract":"Monocular dense prediction has recently seen remarkable success by repurposing pre-trained diffusion models. This opens a promising yet challenging avenue for more efficient multi-task learning paradigm. However, existing multi-task diffusion methods often introduce parameter-heavy adapters, experts, or learnable task...","url_abs":"https://arxiv.org/abs/2606.30370","url_pdf":"https://arxiv.org/pdf/2606.30370v1","authors":"[\"Shuo Zhou\",\"Zhaoxin Li\",\"Xiujuan Chai\"]","published":"2026-06-29T14:34:16Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}