VPG is a training-free inference-time guidance technique that improves autoregressive image and video generation by contrasting model outputs under generated versus corrupted prefixes to strengthen next-step support for the prefix.
arXiv:2512.19680 (2025) 5
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
Semantic Generative Tuning applies segmentation-based generative proxies during post-training to align and improve both understanding and generation in unified multimodal models.
citing papers explorer
-
VPG: Visual Prefix Guidance for Autoregressive Image and Video Generation
VPG is a training-free inference-time guidance technique that improves autoregressive image and video generation by contrasting model outputs under generated versus corrupted prefixes to strengthen next-step support for the prefix.
-
Semantic Generative Tuning for Unified Multimodal Models
Semantic Generative Tuning applies segmentation-based generative proxies during post-training to align and improve both understanding and generation in unified multimodal models.