notesum.ai

Published at December 10

SAT: Spatial Aptitude Training for Multimodal Language Models

cs.CV
cs.AI
cs.GR
cs.RO

Released Date: December 10, 2024

Authors: Arijit Ray1, Jiafei Duan, Reuben Tan, Dina Bashkirova, Rose Hendrix, Kiana Ehsani, Aniruddha Kembhavi, Bryan A. Plummer, Ranjay Krishna, Kuo-Hao Zeng, Kate Saenko

Aff.: 1Boston University

Arxiv: http://arxiv.org/pdf/2412.07755v1