Xin Cai
Scholar

Xin Cai

Google Scholar ID: Uf-cuH4AAAAJ
MMLab, CUHK
Computer Vision
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
158
 
H-index
5
 
i10-index
5
 
Publications
12
 
Co-authors
6
list available
Contact
Emailcaixin16@mails.ucas.ac.cnCVOpen ↗TwitterOpen ↗GitHubOpen ↗
Publications
11 items
DA-VAE: Plug-in Latent Compression for Diffusion via Detail Alignment
2026
Cited
0
MindDriver: Introducing Progressive Multimodal Reasoning for Autonomous Driving
2026
Cited
0
PhotoFramer: Multi-modal Image Composition Instruction
2025
Cited
0
FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
2025
Cited
0
Mixture of Balanced Information Bottlenecks for Long-Tailed Visual Recognition
2025
Cited
0
RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System
2025
Cited
0
LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning
2025
Cited
0
One Framework to Rule Them All: Unifying RL-Based and RL-Free Methods in RLHF
2025
Cited
0
Resume (English only)
Research Experience
  • Interned at Adobe.
Background
  • Interests: 3D Computer Vision, Computational Photography, Gaze Estimation, Artificial General Intelligence. Currently a second-year Ph.D. student at the Multimedia Laboratory (MMLab) of The Chinese University of Hong Kong.
Co-authors
6 total
Tianfan Xue
Tianfan Xue
Information Engineering Department, The Chinese University of Hong Kong
Zhiyuan You
Zhiyuan You
MMLab, The Chinese University of Hong Kong
Shiguang Shan
Shiguang Shan
Professor of Institute of Computing Technology, Chinese Academy of Sciences
Jiabei Zeng
Jiabei Zeng
Institute of Computing Technology, Chinese Academy on Sciences
Co-author 5
Co-author 5
Xilin Chen
Xilin Chen
Institute of Computing Technology, Chinese Academy of Sciences