Shengheng Ma

Guangxi China-Tek Blue Valley Semiconductor Technology Company Ltd., Guangxi, China, Guangxi China-Tek Blue Valley Semiconductor Technology Co.Ltd, China

Papers on Lattice

Total citations

Topics

h-index

Research focus

Computer Vision (1)Multimodal Models (1)Robotics & Embodied AI (1)

Frequent co-authors

Fang Gao (1)Lei Shi (1)Jingfeng Tang (1)Jiabao Wang (1)

Papers (1)

Aug 29, 2025

Aug 29, 2025·also Guangxi China-Tek Blue Valley Semiconductor Technology Co.Ltd, Guangxi China-Tek Blue Valley Semiconductor Technology Company Ltd., USTC

Visual and Textual Commonsense-Enhanced Layout Learning for Vision-and-Language Navigation

VLN agents can navigate more effectively by learning commonsense relationships between rooms and landmarks, thanks to a new method that injects knowledge from ChatGPT, BLIP-2, and Stable Diffusion.

Fang Gao, Lei Shi, Jingfeng Tang +4

Computer Vision Multimodal Models Robotics & Embodied AI

Search

Shengheng Ma

Research focus

Frequent co-authors

Papers (1)