Podobne zapisy

• Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting
  od: Zhu, Xingyu, i wsp.
  Wydane: (2024)
• GuardAlign: Test-time Safety Alignment in Multimodal Large Language Models
  od: Zhu, Xingyu, i wsp.
  Wydane: (2026)
• Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
  od: Zhao, Shuai, i wsp.
  Wydane: (2023)
• Enhancing CLIP Robustness via Cross-Modality Alignment
  od: Zhu, Xingyu, i wsp.
  Wydane: (2025)
• Hand1000: Generating Realistic Hands from Text with Only 1,000 Images
  od: Zhang, Haozhuo, i wsp.
  Wydane: (2024)