MUSE: Unlocking Timestep as Native Task Steering for One-Step Dense Prediction

• URL: http://arxiv.org/abs/2606.30370v1
• Date: Mon, 29 Jun 2026 14:34:16 GMT
• Title: MUSE: Unlocking Timestep as Native Task Steering for One-Step Dense Prediction
• Abstract summary: Monocular dense prediction has recently seen remarkable success by repurposing pre-trained diffusion models.<n>Existing multi-task diffusion methods often introduce parameter-heavy adapters, experts, or learnable task tokens, leading to computational redundancy.<n>We propose Multi-task Unified eStimation via timestep Embedding (MUSE), a parameter-free, single-model multi-tasking approach for dense prediction.
• Score: 6.85882931776959
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Essential Subspace Merging for Multi-Task Learning [78.5390284258307]
  We analyze the output shifts induced by task updates and observe that their energy is concentrated in a small number of principal directions.<n>Most remaining directions carry little task-relevant energy, but their accumulation across multiple task updates can cause severe interference during merging.<n>Based on ESD, we introduce Essential Subspace Merging (ESM), a training-free static merging method.<n>We extend ESM to ESM++, a training-free dynamic merging method that decomposes task-specific residuals into low-rank experts.
  arXiv  Detail & Related papers  (2026-06-17T15:07:11Z)
• Learning Multi-Modal Trajectory Policies for Data-Efficient Robotic Manipulation [21.99077052779724]
  MATE (Multi-Modal MoE) is a novel trajectory prediction framework built upon MoE.<n>We introduce a Multi-Modal MoE architecture to achieve fine-grained sub-modal cosine, and design a cross-modal router for stable and scale-invariant expert assignment.<n>Experiments on robotic ping-pong show that our MATE consistently outperforms prior work under data scarcity.
  arXiv  Detail & Related papers  (2026-05-31T06:35:10Z)
• Ada3Drift: Adaptive Training-Time Drifting for One-Step 3D Visuomotor Robotic Manipulation [53.750389076941396]
  Diffusion-based visuomotor policies capture multimodal action distributions through iterative denoising, but their high inference latency limits real-time robotic control.<n>We propose Ada3Drift, which learns a training-time drifting field that attracts predicted actions toward expert demonstration modes.<n>Ada3Drift achieves state-of-the-art performance while requiring $10times$ fewer function evaluations than diffusion-based alternatives.
  arXiv  Detail & Related papers  (2026-03-12T14:36:53Z)
• Task-oriented Learnable Diffusion Timesteps for Universal Few-shot Learning of Dense Tasks [48.86985692711283]
  Current diffusion model-based applications exploit the power of learned visual representations from multistep forward-backward Markovian processes for single-task prediction tasks.<n>We propose two modules: Task-aware Timestep Selection (TTS) to select ideal diffusion timesteps based on timestep-wise losses and similarity scores, and Timestep Feature Consolidation (TFC) to consolidate the selected timestep features.<n>Our framework effectively achieves superiority in dense prediction performance given only a few support queries.
  arXiv  Detail & Related papers  (2025-12-29T05:19:01Z)
• Uniform Discrete Diffusion with Metric Path for Video Generation [103.86033350602908]
  Continuous-space video generation has advanced rapidly, while discrete approaches lag behind due to error accumulation and long-duration inconsistency.<n>We present Uniform generative modeling and present Uniform pAth (URSA), a powerful framework that bridges the gap with continuous approaches for scalable video generation.<n>URSA consistently outperforms existing discrete methods and achieves performance comparable to state-of-the-art continuous diffusion methods.
  arXiv  Detail & Related papers  (2025-10-28T17:59:57Z)
• A Wireless Foundation Model for Multi-Task Prediction [50.21098141769079]
  We propose a unified foundation model for multi-task prediction in wireless networks that supports diverse prediction intervals.<n>After trained on large-scale datasets, the proposed foundation model demonstrates strong generalization to unseen scenarios and zero-shot performance on new tasks.
  arXiv  Detail & Related papers  (2025-07-08T12:37:55Z)
• MultiMAE Meets Earth Observation: Pre-training Multi-modal Multi-task Masked Autoencoders for Earth Observation Tasks [11.359741665798195]
  This paper explores a more flexible multi-modal, multi-task pre-training strategy for Earth Observation (EO) data.<n>Specifically, we adopt a Multi-modal Multi-task Masked Autoencoder (MultiMAE) that we pre-train by reconstructing diverse input modalities.<n>Our approach exhibits significant flexibility, handling diverse input configurations without requiring modality-specific pre-trained models.
  arXiv  Detail & Related papers  (2025-05-20T22:24:36Z)
• Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports [53.637837706712794]
  We propose a Unified Trajectory Generation model, UniTraj, that processes arbitrary trajectories as masked inputs.<n>Specifically, we introduce a Ghost Spatial Masking (GSM) module, embedded within a Transformer encoder, for spatial feature extraction.<n>We benchmark three practical sports datasets, Basketball-U, Football-U, and Soccer-U, for evaluation.
  arXiv  Detail & Related papers  (2024-05-27T22:15:23Z)
• T-REX: Mixture-of-Rank-One-Experts with Semantic-aware Intuition for Multi-task Large Language Model Finetuning [31.276142111455847]
  Large language models (LLMs) encounter significant adaptation challenges in diverse multitask finetuning.<n>We design a novel framework, mixunderlinetextbfTureunderlinetextbf-of-underlinetextbfRank-onunderlinetextbfE-eunderlinetextbfXper ts (textttT-REX)<n>Rank-1 experts enable a mix-and-match mechanism to quadratically expand the vector subspace of experts with linear parameter overheads, achieving approximate error reduction with optimal
  arXiv  Detail & Related papers  (2024-04-13T12:14:58Z)
• GDTS: Goal-Guided Diffusion Model with Tree Sampling for Multi-Modal Pedestrian Trajectory Prediction [15.731398013255179]
  We propose a novel Goal-Guided Diffusion Model with Tree Sampling for multi-modal trajectory prediction.<n>A two-stage tree sampling algorithm is presented, which leverages common features to reduce the inference time and improve accuracy for multi-modal prediction.<n> Experimental results demonstrate that our proposed framework achieves comparable state-of-the-art performance with real-time inference speed in public datasets.
  arXiv  Detail & Related papers  (2023-11-25T03:55:06Z)
• Perceiver-based CDF Modeling for Time Series Forecasting [25.26713741799865]
  We propose a new architecture, called perceiver-CDF, for modeling cumulative distribution functions (CDF) of time series data. Our approach combines the perceiver architecture with a copula-based attention mechanism tailored for multimodal time series prediction. Experiments on the unimodal and multimodal benchmarks consistently demonstrate a 20% improvement over state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-10-03T01:13:17Z)
• Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning [101.66860222415512]
  Multi-Task Diffusion Model (textscMTDiff) is a diffusion-based method that incorporates Transformer backbones and prompt learning for generative planning and data synthesis. For generative planning, we find textscMTDiff outperforms state-of-the-art algorithms across 50 tasks on Meta-World and 8 maps on Maze2D.
  arXiv  Detail & Related papers  (2023-05-29T05:20:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.