Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator

Documenti analoghi

• InterFeedback: Unveiling Interactive Intelligence of Large Multimodal Models via Human Feedback
  di: Zhao, Henry Hengyuan, et al.
  Pubblicazione: (2025)
• LOVA3: Learning to Visual Question Answering, Asking and Assessment
  di: Zhao, Henry Hengyuan, et al.
  Pubblicazione: (2024)
• SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels
  di: Zhao, Henry Hengyuan, et al.
  Pubblicazione: (2023)
• ControLRM: Fast and Controllable 3D Generation via Large Reconstruction Model
  di: Xu, Hongbin, et al.
  Pubblicazione: (2024)
• Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing
  di: Zeng, Ziyun, et al.
  Pubblicazione: (2025)