MUSE decouples reconstruction and semantic learning in visual tokenization via topological orthogonality, yielding SOTA generation quality and improved semantic performance over its teacher model.
Advances in neural information processing systems , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
VIAR embeds implicit equilibrium layers in visual autoregressive models to achieve ImageNet FID 2.16 with 38.4% of VAR parameters and controllable inference compute.
citing papers explorer
-
MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality
MUSE decouples reconstruction and semantic learning in visual tokenization via topological orthogonality, yielding SOTA generation quality and improved semantic performance over its teacher model.
-
Visual Implicit Autoregressive Modeling
VIAR embeds implicit equilibrium layers in visual autoregressive models to achieve ImageNet FID 2.16 with 38.4% of VAR parameters and controllable inference compute.