הכשרה מתנגדת זהירה בין גנרציה והבנה: MATE

תקציר מקורי באנגליתarXiv:2609.36224v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) combine image generation and visual understanding in a shared backbone. Since generation and understanding are inverse tasks, recent studies self-train UMMs by letting the two branches cooperatively supervise each other. We introduce MATE (Mutually Adversarial self-Training with Evolving data), a reinforcement-learning-based post-training framework in which the two branches instead challenge each other, and the challenges evolve as the model trains. MATE lets generation and understanding take turns to be challenger and solver. Given an image, the understanding branch proposes several candidate descriptions that the generation branch must turn back into similar images, and vice versa. The candidates are scree