MUSE shows that the native timestep embedding in diffusion models acts as a parameter-free steering signal for multi-task monocular depth and normal estimation via manifold decoupling in latent space.
arXiv preprint arXiv:2508.17426 (2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Presents CaloTrilogy, a unified one-step generative model for high-granularity calorimeter showers that combines velocity field integration, learned priors, and physics losses to match SOTA quality.
citing papers explorer
-
MUSE: Unlocking Timestep as Native Task Steering for One-Step Dense Prediction
MUSE shows that the native timestep embedding in diffusion models acts as a parameter-free steering signal for multi-task monocular depth and normal estimation via manifold decoupling in latent space.
-
CaloTrilogy: Toward a Breakthrough in One-Step, End-to-End, Physics-Guided Shower Generation for Modern Calorimeters
Presents CaloTrilogy, a unified one-step generative model for high-granularity calorimeter showers that combines velocity field integration, learned priors, and physics losses to match SOTA quality.