Ye Zhu
Scholar

Ye Zhu

Google Scholar ID: uk5WuyIAAAAJ
Assistant Professor, École Polytechnique
Generative ModelsComputer VisionML4Astrophysics
Citations & Impact
All-time
Citations
443
 
H-index
10
 
i10-index
12
 
Publications
20
 
Co-authors
8
list available
Resume (English only)
Academic Achievements
  • Published papers include 'Dynamic Diffusion Schrödinger Bridge in Astrophysical Observational Inversions' (NeurIPS 2025), 'BNMusic: Blending Environmental Noises into Personalized Music' (NeurIPS 2025), 'The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation' (ICCV 2025), 'D3: Scaling Up Deepfake Detection by Learning from Discrepancy' (CVPR 2025), 'Exploring Magnetic Fields in Molecular Clouds through Denoising Diffusion Probabilistic Models' (APJ 2025), 'Vision + X: A Survey on Multimodal Learning in the Light of Data' (TPAMI 2024).
Research Experience
  • Joined École Polytechnique as a Monge tenure-track assistant professor in 2025; before that, worked as a postdoctoral researcher at Princeton University, collaborating with Prof. Olga Russakovsky.
Education
  • Ph.D. in Computer Science from Illinois Tech, supervised by Prof. Yan Yan; M.S. and B.S. degrees from Shanghai Jiao Tong University (SJTU), and received the French engineering diploma through the dual-degree program with SJTU after studying at École Polytechnique.
Background
  • Research interests: Machine Learning and Computer Vision, with a particular focus on deep generative models (e.g., diffusion models and GANs) and their applications in multimodal settings (e.g., vision, audio, and text) as well as in scientific domains (e.g., astrophysical inversions). Received the MIT EECS Rising Stars Award.
Miscellany
  • Personal interests and other: Co-recruiting a PhD student with Prof. Johannes Lutzeyer on the topic of Graph-Guided Multimodal Generation and Control.