Documenti analoghi

• LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment
  di: Wang, Yibin, et al.
  Pubblicazione: (2024)
• SARA: Structural and Adversarial Representation Alignment for Training-efficient Diffusion Models
  di: Chen, Hesen, et al.
  Pubblicazione: (2025)
• EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models
  di: Tan, Zhiyu, et al.
  Pubblicazione: (2024)
• GRPose: Learning Graph Relations for Human Image Generation with Pose Priors
  di: Yin, Xiangchen, et al.
  Pubblicazione: (2024)
• GaussianIP: Identity-Preserving Realistic 3D Human Generation via Human-Centric Diffusion Prior
  di: Tang, Zichen, et al.
  Pubblicazione: (2025)