Yitao Xu (徐一涛)

Welcome to my homepage! I am currently a 2nd year PhD student at École polytechnique fédérale de Lausanne (EPFL) in the EDIC program. Before that, I was a master's student at KTH Royal Institute of Technology, majoring in Machine Learning. In 2022 Fall and 2023 Spring, I was an exchange master's student in Computer Science at EPFL.

I got my B.Eng degree in Computer Science and Technology at Beihang University (BUAA). I worked as a research student at State Key Laboratory of Software Development Environment (NLSDE), advised by Prof.Xianglong Liu, and I also finished my bachelor's thesis project focusing on rectifying texture bias exposed in deep neural network there. After graduating from BUAA, I became a Machine Learning Intern at DiDi AI Labs, where I was led by Dr. Zhengping Che and Prof.Jian Tang. Beginning in 12.2020, I spent a wonderful winter at Tsinghua Laboratory of Brain and Intelligence (THBI) under the supervision of Prof.Jia Liu, studying intuitive physics engine and stability inference with convolutional neural networks.

Email  /  CV  /  Linkedin  /  Google Scholar  /  Github

profile photo
Research

I'm interested in Computer Vision and Machine Learning. Particularly, I focus on:

  • 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
I believe studying bio-inspired models and investigating the difference between humans and machines can help us achieve silicon-based artificial human intelligence!

Publications
"*" means equal contribution
AdaNCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer
Yitao Xu, Tong Zhang, Sabine Süsstrunk
NeurIPS, 2024
paper / code (Coming Soon!)

We propose AdaNCA, inserting NCA into ViTs as plug-and-play adaptors for enhancing their robustness. We develop a unified perspective of NCA and ViT in terms of token interaction learning. Our work takes the first step to scale NCA up to solve large-scale computer vision problems, and proves that NCA can be practically utilized to improve the robustness of current vision transformer models.

Mesh Neural Cellular Automata
Ehsan Pajouheshgar*, Yitao Xu*, Alexander Mordvintsev, Eyvind Niklasson, Tong Zhang, Sabine Süsstrunk
SIGGRAPH, 2024
project page / arXiv / code

MeshNCA is a comprehensive framework for 3D texture synthesis. It is compatible with image or text targets, and enjoys various test-time properties such as texture density control, grafting, and mesh generalization. Play with our demo!

NoiseNCA: Noisy Seed Improves Spatio-Temporal Continuity of Neural Cellular Automata
Ehsan Pajouheshgar, Yitao Xu, Sabine Süsstrunk
ALife, 2024 (Best Student Paper Award)
project page / arXiv / code (Coming Soon!)

We examine the behaviors of NCA at the spatio-temporal limit and find it struggling to generate correct patterns. We propose a simple yet effective solution by initializing the seeds with noises. The increased spatio-temporal continuity enables several test-time controls, including anisotropic scaling, multi-scale pattern formation, and continuous speed adjustment. Play with our demo!

Emergent Dynamics in Neural Cellular Automata
Yitao Xu, Ehsan Pajouheshgar, Sabine Süsstrunk
ALife, 2024
arXiv / code (Coming Soon!)

We investigate the relationship between the NCA architecture and the emergent dynamics of the trained models.

DyNCA: Real-time Dynamic Texture Synthesis Using Neural Cellular Automata
Ehsan Pajouheshgar*, Yitao Xu*, Tong Zhang, Sabine Süsstrunk
CVPR, 2023
project page / arXiv / code

We propose Dynamic Neural Cellular Automata (DyNCA), a framework for real-time and controllable dynamic texture synthesis. Play with our demo!

Understanding adversarial robustness via critical attacking route
Tianlin Li, Aishan Liu, Xianglong Liu, Yitao Xu, Chongzhi Zhang, Xiaofei Xie
Information Sciences, 2021
paper

We believe that adversarial noises are amplified and propagated through the critical attacking route, identified by the proposed algorithm.

Spatiotemporal Attacks for Embodied Agents
Aishan Liu, Tairan Huang, Xianglong Liu, Yitao Xu, Yuqing Ma, Xinyun Chen, Steve Maybank, Dacheng Tao
ECCV, 2020
paper

We take the first step to study adversarial attacks for embodied agents. We generate spatiotemporal perturbations to form 3D adversarial examples, exploiting the interaction history in both the temporal and spatial dimensions.

Interpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivity
Chongzhi Zhang, Aishan Liu, Xianglong Liu, Yitao Xu, Hang Yu, Yuqing Ma, Tianlin Li
IEEE Transactions on Image Processing, 2020
paper

We explain adversarial robustness for deep models from a new perspective of neuron sensitivity which is measured by neuron behavior variation intensity against benign and adversarial examples.


Design