About

About

• a final-year Ph.D. candidate at Carnegie Mellon University
• working with Prof. László A. Jeni, Prof. Min Xu, and Prof. Bhiksha Raj
• previously worked with
  • Chaoyang Wang, Ashkan Mirzaei, Peter Wonka, and Sergey Tulyakov at Snap Creative Vision
  • Charles Herrmann, Junhwa Hur, Yinxiao Li, and Ming-Hsuan Yang at Google DeepMind
  • Kamran Ghasedi Dizaji and Tadas Baltrušaitis at Microsoft Applied Sciences Group
  • Chun-Hao Huang, Tuanfeng Wang, Duygu Ceylan, and Jimei Yang at Adobe Research
  • Xun Guo and Yan Lu at Microsoft Research Asia

Publications

Multi-Object System Identification from Videos

"identify multiple dynamical systems from a single video"

Chunjiang Liu, Xiaoyuan Wang, Qingran Lin, Albert Xiao, Haoyu Chen, Shizheng Wen, Hao Zhang, Lu Qi, Ming-Hsuan Yang, Laszlo A. Jeni, Min Xu, Yizhou Zhao

International Conference on Learning Representations (ICLR), 2026

Paper

---

HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis

"holistic Gaussian Splatting for embodied view synthesis"

Xiaoyuan Wang, Yizhou Zhao, Botao Ye, Xiaojun Shan, Weijie Lyu, Lu Qi, Kelvin CK Chan, Yinxiao Li, Ming-Hsuan Yang

Advances in Neural Information Processing Systems (NeurIPS), 2025

Paper

---

Toward Material-Agnostic System Identification from Videos

"identify physical system parameters from video regardless of object material"

Yizhou Zhao, Haoyu Chen, Chunjiang Liu, Zhenyang Li, Charles Herrmann, Junhwa Hur, Yinxiao Li, Ming-Hsuan Yang, Bhiksha Raj, Min Xu

International Conference on Computer Vision (ICCV), 2025

Paper Code

---

Total-Editing: Head Avatar with Editable Appearance, Motion, and Lighting

"one framework to edit appearance, motion, and lighting in 3D head avatars"

Yizhou Zhao, Chunjiang Liu, Haoyu Chen, Bhiksha Raj, Min Xu, Tadas Baltrusaitis, Mitch Rundle, HsiangTao Wu, Kamran Ghasedi

International Conference on Computer Vision Workshops (ICCVW), 2025

Paper

---

Metric from Human: Zero-shot Monocular Metric Depth Estimation via Test-time Adaptation

"zero-shot metric depth from a single image via test-time adaptation to human priors"

Yizhou Zhao, Hengwei Bian, Kaihua Chen, Pengliang Ji, Liao Qu, Shao-yu Lin, Weichen Yu, Haoran Li, Hao Chen, Jun Shen, Bhiksha Raj, Min Xu

Advances in Neural Information Processing Systems (NeurIPS), 2024

Paper Code

---

CryoSAM: Training-Free CryoET Tomogram Segmentation with Foundation Models

"foundation models segment cryo-ET tomograms without any training"

Yizhou Zhao, Hengwei Bian, Michael Mu, Mostofa Rafid Uddin, Zhenyang Li, Xiang Li, Tianyang Wang, Min Xu

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2024

Paper Code

---

Synergistic Global-space Camera and Human Reconstruction from Videos

"joint global-space camera and human reconstruction from monocular video"

Yizhou Zhao, Tuanfeng Yang Wang, Bhiksha Raj, Min Xu, Jimei Yang, Chun-Hao Paul Huang

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Project Page Paper

---

Alignment-guided Temporal Attention for Video Action Recognition

"alignment tells the model where to attend in time for video action recognition"

Yizhou Zhao, Zhenyang Li, Xun Guo, Yan Lu

Advances in Neural Information Processing Systems (NeurIPS), 2022

Paper

---

Semantic-aligned Fusion Transformer for One-shot Object Detection

"semantic-aligned fusion for one-shot object detection"

Yizhou Zhao, Xun Guo, Yan Lu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Paper

---

Awards

• SoftBank Group–Arm Fellowship, 2025
• CVPR Outstanding Reviewer, 2025

Mentees

• Chunjiang Liu
• Haoyu Chen
• Xiaoyuan Wang
• Albert Xiao
• Hengwei Bian
• Michael Mu