Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation

Documenti analoghi

• Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling
  di: Zheng, Shuhong, et al.
  Pubblicazione: (2025)
• ArchGPT: Understanding the World's Architectures with Large Multimodal Models
  di: Wang, Yuze, et al.
  Pubblicazione: (2025)
• Kubrick: Multimodal Agent Collaborations for Synthetic Video Generation
  di: He, Liu, et al.
  Pubblicazione: (2024)
• DanceEditor: Towards Iterative Editable Music-driven Dance Generation with Open-Vocabulary Descriptions
  di: Zhang, Hengyuan, et al.
  Pubblicazione: (2025)
• Break-for-Make: Modular Low-Rank Adaptations for Composable Content-Style Customization
  di: Xu, Yu, et al.
  Pubblicazione: (2024)