Qingyu Shi
Scholar

Qingyu Shi

Google Scholar ID: VpSqhJAAAAAJ
Peking University
computer visiondiffusionmultimodal
Google Scholar↗
Citations & Impact
All-time
Citations
51
 
H-index
5
 
i10-index
2
 
Publications
7
 
Co-authors
13
list available
Contact
No contact links provided.
Publications
12 items
VQKV: High-Fidelity and High-Ratio Cache Compression via Vector-Quantization
2026
Cited
0
Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models
2026
Cited
0
RecTok: Reconstruction Distillation along Rectified Flow
2025
Cited
0
Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation
2025
Cited
0
Personalized Safety Alignment for Text-to-Image Diffusion Models
2025
Cited
0
Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
2025
Cited
0
On Path to Multimodal Generalist: General-Level and General-Bench
2025
Cited
0
An Empirical Study of GPT-4o Image Generation Capabilities
2025
Cited
0
Resume (English only)
Co-authors
13 total
Xiangtai Li
Xiangtai Li
Research Scientist, Tiktok, SG; MMLab@NTU
Lu Qi
Lu Qi
Insta360 | Wuhan Univeristy
Jinbin Bai
Jinbin Bai
National University of Singapore
Yunhai Tong
Yunhai Tong
Peking University
Jianzong Wu
Jianzong Wu
PhD Student in School of Intelligence Science and Technology, Peking University
Haobo Yuan
Haobo Yuan
UC Merced
Shilin Xu
Shilin Xu
Peking University
Jingbo Wang
Jingbo Wang
Shanghai AI Laboratory