2 papers
cs.CV2026
VISTA: Test-Time Compositional Alignment for Visual Autoregressive Generation
Hossein Shahabadi, Niki Sepasian, Mahdieh Soleymani Baghshah
Visual autoregressive (VAR) models offer fast, high-quality text-to-image generation but still fail at attribute binding and spatial relations. Existing VAR test-time methods searc…
cs.CV2025
Infinity and Beyond: Compositional Alignment in VAR and Diffusion T2I Models
Hossein Shahabadi, Niki Sepasian, Arash Marioriyad +2
Achieving compositional alignment between textual descriptions and generated images - covering objects, attributes, and spatial relationships - remains a core challenge for modern…