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.
Staying on the manifold: Geometry-aware noise injection.arXiv preprint arXiv:2509.20201
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Evolving lifted data vectors under a chaotic dynamical system before softmax classification accelerates training and improves accuracy over standard and lifted-only baselines on perturbed orthogonal vectors.
Derives an asymptotic equivalent for the Representation Gap in equivariant diffusion models, showing it depends primarily on the intrinsic dimension of the task.
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.
-
Enhancing classification accuracy through chaos
Evolving lifted data vectors under a chaotic dynamical system before softmax classification accelerates training and improves accuracy over standard and lifted-only baselines on perturbed orthogonal vectors.
-
Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective
Derives an asymptotic equivalent for the Representation Gap in equivariant diffusion models, showing it depends primarily on the intrinsic dimension of the task.