Xinhao Cai

About Me

I am a postdoctoral fellow in AI Chip Center for Emerging Smart Systems (ACCESS) at the Hong Kong University of Technology and Science (HKUST), advised by Prof. Kwang-Ting (Tim) Cheng. This postdoctoral fellowship is supported by Hong Kong’s Innovation and Technology Fund (ITF), which is administered by the Innovation and Technology Commission (ITC).

I received my Ph.D. degree from the school of Computer Science and Engineering at Nanjing University of Science and Technology (NJUST), honored to be supervised by Prof. Yazhou Yao. During my Ph.D., I was a long-term research intern at Zhejiang University, honored to be supervised by Prof. Wenguan Wang. Before that, I received my undergraduate degree from the college of Qian-Xuesen, Nanjing University of Science and Technology.

Research Interests

• Generation Model: Diffusion-based Foundation Model, Layout-to-image Generation
• Perceptron Model: Depth Estimation, Remote Sensing Object Detection, General Object Detection

News

• [June 2026] I received my Ph.D. degree from Nanjing University of Science and Technology.
• [June 2026] Our paper “PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection” is accepted to ECCV 2026!
• [Feb. 2026] Our paper “Iris: Bringing Real-World Priors into Diffusion Model for Monocular Depth Estimation” is accepted to CVPR 2026!
• [Feb. 2026] Our paper “PEARL: Geometry Aligns Semantics for Training-Free Open-Vocabulary Semantic Segmentation” is accepted to CVPR 2026!
• [Jan. 2026] Our paper “Beyond Frequency: Scoring-Driven Debiasing for Object Detection via Blueprint-Prompted Image Synthesis” is accepted to ICLR 2026!
• [July 2025] Our paper “Cycle-Consistent Learning for Joint Layout-to-Image Generation and Object Detection” is accepted to ICCV 2025!
• [Feb. 2025] Our paper “Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection” is accepted to CVPR 2025!
• [Feb. 2024] Our paper “Poly Kernel Inception Network for Remote Sensing Detection” is accepted to CVPR 2024!
• [May 2023] Our paper “Automated Object Recognition in High-resolution Optical Remote Sensing Imagery” is accepted to NSR!
• [May 2023] We win the third place in Huiyan ‘Tianzhi Cup’ Artificial Intelligence Competition (天智杯), receiving a grand prize of ¥200,000!
• [Mar. 2023] We win the first place in Guangdong-Hong Kong-Macau Greater Bay Area (Huangpu) International Algorithm Competition (粤港澳大湾区黄埔算法算例大赛), receiving a grand prize of ¥600,000!
• [June 2022] We win the first place in Teddy Cup Data Mining Challenge (泰迪杯数据挖掘挑战赛), receiving a grand prize of ¥30,000!

Publications

Services

Conference Reviewers

• Annual Conference on Neural Information Processing Systems (NeurIPS)
• International Conference on Machine Learning (ICML)
• International Conference on Learning Representations (ICLR)
• ACM International Conference on Multimedia (ACM MM)

Journal Reviewers

• IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
• IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
• Information Fusion (IF)
• Neural Networks (NN)
• Neurocomputing
• The Visual Computer

Powered by Jekyll and Minimal Light theme.