Search NASA⌕ Search
Home/Archive/DOE OSTI

DOE OSTI · 3375199

Oracle-RLAIF: Improving Multi-modal Video Model Training with Reinforcement Learning from AI Feedback with Ranked Preferences

Shi, Derek [University of California Los Angeles]·Glatt, Ruben [Lawrence Livermore National Laboratory]·Klymko, Christine [Lawrence Livermore National Laboratory]·Mohole, Shubham·Kushwaha, Shashank·Choi, Hongjun [Lawrence Livermore National Laboratory]·Sakla, Wesam [Lawrence Livermore National Laboratory]·Leno Da Silva, Leno [Lawrence Livermore National Laboratory]
View original source ↗Read source document ↗Export metadata ↓

Abstract

The source did not provide an abstract. Follow the original record for more information.

Explore related subjects

Mathematics and Computing

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Shi, Derek [University of California Los Angeles], Glatt, Ruben [Lawrence Livermore National Laboratory], Klymko, Christine [Lawrence Livermore National Laboratory], Mohole, Shubham, Kushwaha, Shashank, Choi, Hongjun [Lawrence Livermore National Laboratory], Sakla, Wesam [Lawrence Livermore National Laboratory], Leno Da Silva, Leno [Lawrence Livermore National Laboratory]. 2026-06-24. Oracle-RLAIF: Improving Multi-modal Video Model Training with Reinforcement Learning from AI Feedback with Ranked Preferences. https://www.osti.gov/biblio/3375199

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

DOE OSTI2026

High-Order Mesh r-Adaptivity with Tangential Relaxation and Guaranteed Mesh Validity

High-order meshes are crucial for achieving optimal convergence rates in curvilinear domains, preserving symmetry, and aligning with key flow features in moving mesh simulations [1], but their quality is challenging to control. In prior work, we have developed techniques based on Target-Matrix Optimization Paradigm (TMOP) to adapt a given high-order mesh to the geometry and solution of the partial differential equation (PDE) [2, 3]. Here, we extend this framework to address two key gaps in the literature for highorder mesh 𝑟-adaptivity. First, we introduce tangential relaxation on curved surfaces using solely the discrete mesh representation, eliminating the need for access to underlying geometry (e.g., CAD model). Second, we ensure a continuously positive Jacobian determinant throughout the domain. This determinant positivity is essential for using the high-order mesh resulting from 𝑟-adaptivity with arbitrary quadrature schemes in simulations. The proposed approach is demonstrated to be robust using a variety of numerical experiments.

Mathematics and Computing↗