Scholar
Xiaoyu Qin
Google Scholar ID: 3WLGlb4AAAAJ
Tsinghua University
Citations & Impact
Citations
180
H-index
10
i10-index
10
Publications
20
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- Published several papers, including 'HarmoniVox: Painting Voices to Match the Avatar's Soul' (ACM MM '25), 'DEPO: Enhancing E-commerce Image Background Generation with Short Trajectory Direct Expected Preference Optimization' (ACM MM '25), 'V-CASS: Vision-context-aware Expressive Speech Synthesis for Enhancing User Understanding of Videos' (IJCNN '25), etc. Also participated in various research works like 'Minimal Impact ControlNet: Advancing Multi-ControlNet Integration' (ICLR '25), 'VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling' (ACM MM '24, Oral), etc.
Research Experience
- Served as a Postdoctoral Fellow at the Department of Computer Science and Technology, Tsinghua University, participating in multiple research projects such as HarmoniVox, DEPO, V-CASS, etc.
Education
- No specific education background information provided.
Background
- Postdoctoral Fellow at the Department of Computer Science and Technology, Tsinghua University, in cooperation with Prof. Jia Jia. Current research focus is on Human-AI Interaction. Research interests include Multimedia, Artificial Intelligence, Optimization, and their applications. Past research interests also include Theory of Evolutionary Algorithms.
Miscellany
- No additional personal information or hobbies provided.
