Data Science Wire

MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts

arXiv cs.CV1mo4 min read

arXiv:2607.00371v1 Announce Type: new Abstract: Visual AutoRegressive modeling (VAR) has pioneered a coarse-to-fine multi-scale autoregressive generative paradigm, demonstrating strong capabilities in image generation. However, VAR still suffers from inherent deficiencies in multi-scale representation learning. Specifically, lower scales primarily capture global semantics, while higher scales focus on fine-grained details. Employing a shared architecture across scales induces optimization conflicts. Moreover, due to the causal autoregressive process, inaccurate semantics at early scales can pr

Read the full story at arXiv cs.CV

More in Machine Learning