2 papers
cs.CV2026
Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling
Meimingwei Li, Stefan Andreas Baumann, Felix Krause +1
Visual Autoregressive Models (VAR) generate images through next-scale prediction, producing all tokens within each scale in parallel. We show that this parallel decoding constitute…
cs.CV2026
Guiding Token-Sparse Diffusion Models
Felix Krause, Stefan Andreas Baumann, Johannes Schusterbauer +4
Diffusion models deliver high quality in image synthesis but remain expensive during training and inference. Recent works have leveraged the inherent redundancy in visual content t…