Shitong Shao
Scholar

Shitong Shao

Google Scholar ID: hmUOaNcAAAAJ
The Hong Kong University of Science and Technology (Guangzhou)
Efficient Computer VisionDiffusion ModelsInference-heavy Algorithms
Google Scholar↗
Citations & Impact
All-time
Citations
411
 
H-index
14
 
i10-index
19
 
Publications
20
 
Co-authors
10
list available
Contact
No contact links provided.
Publications
20 items
CRAFT: Aligning Diffusion Models with Fine-Tuning Is Easier Than You Think
2026
Cited
0
Reflective Flow Sampling Enhancement
2026
Cited
0
FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters
2026
Cited
0
Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation
2026
Cited
0
Optimizing Few-Step Generation with Adaptive Matching Distillation
2026
Cited
0
Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better
2026
Cited
0
PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers
2026
Cited
0
LAST: LeArning to Think in Space and Time for Generalist Vision-Language Models
2025
Cited
0
Resume (English only)
Co-authors
10 total
Huanran Chen
Huanran Chen
PhD student, Tsinghua SAIL
Zikai Zhou
Zikai Zhou
Hong Kong University of Science and Technology(Guang Zhou)
Zeke Xie
Zeke Xie
Assistant Professor, The Hong Kong University of Science and Technology (Guangzhou)/ PI, xLeaF Lab
Zhiqiang Shen
Zhiqiang Shen
Assistant Professor at Mohamed bin Zayed University of Artificial Intelligence
Co-author 5
Co-author 5
Xinxiao Wu (吴心筱)
Xinxiao Wu (吴心筱)
Beijing Institute of Technology
Li, Lu-Jun
Li, Lu-Jun
Professor (Associate)
Xu Dai
Xu Dai
Shanghai Artificial Intelligence Laboratory