most citedSWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?

2 citations · 2 across the 3 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2025

GamiBench: Evaluating Spatial Reasoning and 2D-to-3D Planning Capabilities of MLLMs with Origami Folding Tasks

Ryan Spencer, Roey Yaari, Ritvik Vemavarapu +3

Multimodal large language models (MLLMs) are proficient in perception and instruction-following, but they still struggle with spatial reasoning: the ability to mentally track and m…