Spotlight: Identifying and Localizing Video Generation Errors Using VLMs

Documenti analoghi

• SPIKE-RL: Video-LLMs meet Bayesian Surprise
  di: Ravi, Sahithya, et al.
  Pubblicazione: (2025)
• Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events
  di: Chinchure, Aditya, et al.
  Pubblicazione: (2024)
• From Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language Models
  di: Bhatia, Mehar, et al.
  Pubblicazione: (2024)
• TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models
  di: Chinchure, Aditya, et al.
  Pubblicazione: (2023)
• Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Models
  di: Shukla, Pushkar, et al.
  Pubblicazione: (2025)