Cite
Notes
Only stored in your browser.
Attribution
VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment
arXiv 2024
Learning Action and Reasoning-Centric Image Editing from Videos and Simulations
from 2 papers
Siva Reddy
Aaron Courville
Alessandro Sordoni
Amirhossein Kazemnejad
Benno Krojer
Christopher Pal
Dheeraj Vattikonda
Luis Lara
Milad Aghajohari
Nicolas Le Roux