UMM-JEPA: Generative Pretraining via Masked Next-Scale Representation Prediction for Unified Multimodal Models
Unified multimodal models can support both visual understanding and generation, yet generative training does not necessarily improve understanding. We argue that this limitation may arise from a mismatch between the representation targeted by generation and the perceptual representation used for…
arXiv - cs.CV (CV)2 min read