UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning

Documenti analoghi

• UniMoD: Efficient Unified Multimodal Transformers with Mixture-of-Depths
  di: Mao, Weijia, et al.
  Pubblicazione: (2025)
• Show-o2: Improved Native Unified Multimodal Models
  di: Xie, Jinheng, et al.
  Pubblicazione: (2025)
• The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation
  di: Mao, Weijia, et al.
  Pubblicazione: (2025)
• DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles
  di: Zhao, Rui, et al.
  Pubblicazione: (2025)
• Show-o: One Single Transformer to Unify Multimodal Understanding and Generation
  di: Xie, Jinheng, et al.
  Pubblicazione: (2024)