2 papers
cs.CL2025
Visually Descriptive Language Model for Vector Graphics Reasoning
Zhenhailong Wang, Joy Hsu, Xingyao Wang +4
Despite significant advancements, large multimodal models (LMMs) still struggle to bridge the gap between low-level visual perception -- focusing on shapes, sizes, and layouts -- a…
cs.CL2025
Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks
Zhenhailong Wang, Haiyang Xu, Junyang Wang +5
Smartphones have become indispensable in modern life, yet navigating complex tasks on mobile devices often remains frustrating. Recent advancements in large multimodal model (LMM)-…