@misc{indiciaea005883af063,
  title = {Oracle-RLAIF: Improving Multi-modal Video Model Training with Reinforcement Learning from AI Feedback with Ranked Preferences},
  author = {Shi, Derek [University of California Los Angeles] and Glatt, Ruben [Lawrence Livermore National Laboratory] and Klymko, Christine [Lawrence Livermore National Laboratory] and Mohole, Shubham and Kushwaha, Shashank and Choi, Hongjun [Lawrence Livermore National Laboratory] and Sakla, Wesam [Lawrence Livermore National Laboratory] and Leno Da Silva, Leno [Lawrence Livermore National Laboratory]},
  year = {2026},
  url = {https://www.osti.gov/biblio/3375199},
  note = {Source identifier: 3375199}
}