Preprint
Aug 2026
VISTA: Test-Time Compositional Alignment for Visual Autoregressive Generation
VISTA is the first gradient-based test-time alignment framework for next-scale autoregressive image generation, and introduces the mechanisms needed to make such optimization stable across scales, together with an extensible objective space that any differentiable constraint on cross-attention can plug into.
Hossein Shahabadi, Niki Sepasian, M. Baghshah
· 0 citations