The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention

Documenti analoghi

• VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval
  di: Wu, Di, et al.
  Pubblicazione: (2025)
• CompAlign: Improving Compositional Text-to-Image Generation with a Complex Benchmark and Fine-Grained Feedback
  di: Wan, Yixin, et al.
  Pubblicazione: (2025)
• The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual Subjects
  di: Wan, Yixin, et al.
  Pubblicazione: (2024)
• Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation
  di: Wan, Yixin, et al.
  Pubblicazione: (2024)
• MotionEdit: Benchmarking and Learning Motion-Centric Image Editing
  di: Wan, Yixin, et al.
  Pubblicazione: (2025)