Scholar
Yitao Xu
Google Scholar ID: jvCvNPQAAAAJ
PhD student, EPFL
Citations & Impact
Citations
321
H-index
5
i10-index
5
Publications
13
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- - AdaNCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer, NeurIPS, 2024
- - Mesh Neural Cellular Automata, SIGGRAPH, 2024
- - NoiseNCA: Noisy Seed Improves Spatio-Temporal Continuity of Neural Cellular Automata, ALife, 2024 (Best Student Paper Award)
- - Emergent Dynamics in Neural Cellular Automata, ALife, 2024
- - DyNCA: Real-time Dynamic Texture Synthesis Using Neural Cellular Automata, CVPR, 2023
Research Experience
- - PhD student at École polytechnique fédérale de Lausanne (EPFL) in the EDIC program
- - Master's student at KTH Royal Institute of Technology
- - Undergraduate at Beihang University (BUAA), conducted research at State Key Laboratory of Software Development Environment (NLSDE)
- - Machine Learning Intern at DiDi AI Labs
- - Research assistant at Tsinghua Laboratory of Brain and Intelligence (THBI)
Education
- - Currently a 3rd year PhD student at École polytechnique fédérale de Lausanne (EPFL) in the EDIC program
- - Master's student at KTH Royal Institute of Technology, majoring in Machine Learning
- - Exchange master's student in Computer Science at EPFL during 2022 Fall and 2023 Spring
- - B.Eng degree in Computer Science and Technology from Beihang University (BUAA), worked as a research student at State Key Laboratory of Software Development Environment (NLSDE), advised by Prof. Xianglong Liu
- - Machine Learning Intern at DiDi AI Labs, led by Dr. Zhengping Che and Prof. Jian Tang
- - Research assistant at Tsinghua Laboratory of Brain and Intelligence (THBI) under the supervision of Prof. Jia Liu, starting from Dec 2020
Background
- Research interests include Computer Vision and Machine Learning, particularly neural cellular automata and self-organizing systems, interpretability of adversarial attacks and adversarial robustness, different cognition biases between humans and deep-learning based computer vision models. Believes that studying bio-inspired models and investigating the difference between humans and machines can help achieve silicon-based artificial human intelligence.
Miscellany
- Personal interests not provided
Co-authors