Scholar
Mingyuan Zhou
Google Scholar ID: hZFzJ6QAAAAJ
Amazon
Citations & Impact
Citations
126
H-index
7
i10-index
5
Publications
16
Co-authors
9
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- - Selected Publications:
- - UltrAvatar: A Realistic Animatable 3D Avatar Diffusion Model with Authenticity Guided Textures
- - OmniMotionGPT: Animal Motion Generation with Limited Data
- - Openstory++: A Large-scale Dataset and Benchmark for Instance-aware Open-domain Visual Storytelling
- - Polarimetric Helmholtz Stereopsis
- - Shape and Reflectance Reconstruction Using Concentric Multi-Spectral Light Field
- - 3D Face Reconstruction using Color Photometric Stereo with Uncalibrated Near Point Lights
- - Structure from Motion on XSlit Cameras
- - Hybrid sensing face detection and registration for low-light and unconstrained conditions
- - Content Aware Image Pre-Compensation
- - Rotational Crossed-Slit Light Fields
Research Experience
- - Amazon: Senior Applied Scientist, driving innovation at the intersection of science and product intelligence.
- - InnoPeak Technology (OPPO US Research Center): Senior Staff Research Scientist, focusing on AIGC foundation models.
Education
- - PhD in Computer Science from the University of Delaware, advised by Prof. Jingyi Yu.
- - MS in Computer Engineering from Stevens Institute of Technology.
Background
- - Currently a Senior Applied Scientist at Amazon, focusing on Large Language Models (LLMs), Multimodal LLMs (M-LLMs), Vision-Language Models (VLMs), image/video generation, and foundation models for product relationships.
- - Previously, a Senior Staff Research Scientist at InnoPeak Technology (OPPO US Research Center), focusing on the development of AIGC foundation models.
- - Research interests span deep learning, computer vision, computer graphics, and computational photography.
Miscellany
- - Personal interests and hobbies not provided.
