Multimodal Learning
Connecting visual, textual, and spatial signals so models can answer richer questions about scenes.
Peking University / Wangxuan Institute of Computer Technology
Wentao Mo
PhD student at Peking University working on multimodal learning, computer vision, and embodied AI.
I joined the Wangxuan Institute of Computer Technology (WICT), PKU in September 2022 for my PhD, supervised by Prof. Yang Liu. My work explores how vision, language, and 3D scene understanding can support stronger reasoning in embodied environments.
Research
Building blocks for visual reasoning
Computer Vision
Studying 2D and 3D scene understanding with an emphasis on practical visual question answering.
Embodied AI
Designing evaluation and pre-training resources that help agents reason in grounded environments.
Publications
Selected work
Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs
Wentao Mo, Yang Liu
PDF soon Code soon arXiv soon Project soon
Advancing 3D Scene Understanding with MV-ScanQA Multi-View Reasoning Evaluation and TripAlign Pre-training Dataset
Wentao Mo, Qingchao Chen, Yuxin Peng, Siyuan Huang, Yang Liu
Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA
Wentao Mo, Yang Liu
3D Vision and Language Pretraining with Large-Scale Synthetic Data
Dejie Yang, Zhu Xu, Wentao Mo, Qingchao Chen, Siyuan Huang, Yang Liu
Contact