VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL

Documenti analoghi

• Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning
  di: Dai, Fengyuan, et al.
  Pubblicazione: (2024)
• Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference
  di: Liu, Ting, et al.
  Pubblicazione: (2024)
• LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models
  di: Cheng, Yu, et al.
  Pubblicazione: (2025)
• VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders
  di: Liu, Xuyang, et al.
  Pubblicazione: (2023)
• Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference
  di: Zhao, Han, et al.
  Pubblicazione: (2024)