Scholar
Mingxuan Liu
Google Scholar ID: egL5-LsAAAAJ
University of Trento
Citations & Impact
Citations
118
H-index
4
i10-index
3
Publications
11
Co-authors
8
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- - Paper 'UrbanVerse: Scaling Urban Simulation by Watching City-Tour Videos' accepted to arXiv
- - Paper 'Organizing Unstructured Image Collections using Natural Language' accepted to arXiv
- - Selected as Outstanding Reviewer for CVPR 2025
- - Received $5,000 research funding from OpenAI
- - Paper 'Incremental Novel Class Discovery with Large Scale Pre-trained Models' accepted as an Oral paper at ICPR 2024
- - Filed first US Patent: 'A Method for Using Semantic Hierarchy Trees to Increase the Robustness of Open-vocabulary Object Detection Models'
- - Paper 'Open-vocabulary Object Detection with Semantic Hierarchy' accepted as a Highlight paper at CVPR 2024, 2.8% acceptance rate
- - Paper 'Discovering Fine-grained Semantic Concepts with LLMs' accepted to ICLR 2024
Research Experience
- - PhD student at University of Trento, researching deep learning and computer vision
- - Visiting Researcher at UCLA, working on automatic urban simulation scene creation, advised by Prof. Bolei ZHOU
- - Visiting Researcher at NAVER LABS Europe, exploring open-vocabulary object detection, supervised by Gabriela CSURKA, Riccardo VOLPI, and Tyler L. HAYES, led by Diane Larlus
- - Innovation Engineer at SIEMENS Smart Infrastructure Division, designing IoT-based automation solutions
Education
- - PhD student at University of Trento, supervised by Prof. Elisa RICCI and Prof. Zhun ZHONG
- - Master's degree in Intelligent Autonomous Systems from KTH Royal Institute of Technology (Sweden), Summa Cum Laude
- - Master's degree in Mechatronics Engineering from University of Trento (Italy), Summa Cum Laude
Background
- - PhD student in Deep Learning and Computer Vision
- - Research interests: Training open-world machines to see, understand, and reason about our chaotic visual, semantic, and physical world
- - Professional fields: Knowledge discovery, open-vocabulary recognition, vision and language, urban embodied AI simulation
Miscellany
- - Personal interests: Not specified
