Junyi Wu
Scholar

Junyi Wu

Google Scholar ID: e-0gPdMAAAAJ
Shanghai Jiao Tong University
Efficient AIModel AccelerationModel Compression
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
9
 
H-index
2
 
i10-index
0
 
Publications
3
 
Co-authors
0
 
Contact
Emailjunyiwu2005@outlook.comGitHubOpen ↗
Publications
1 items
AdaTSQ: Pushing the Pareto Frontier of Diffusion Transformers via Temporal-Sensitivity Quantization
2026
Cited
0
Resume (English only)
Academic Achievements
  • Publications:
  • - BalanceGS accepted by ASP-DAC 2026
  • - QuantCache accepted by ICCV 2025
  • - SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting accepted by ISCA 2025
  • - DVD-Quant: Data-free Video Diffusion Transformers Quantization under review
Research Experience
  • Worked closely with Prof. Guohao Dai and Prof. Yulun Zhang on research projects.
Education
  • Undergraduate student at the Department of EE, Shanghai Jiao Tong University (SJTU) (2023.9 - Present), Advisors: Prof. Guohao Dai, Prof. Yulun Zhang.
Background
  • Research Interests: Acceleration and compression of LLM/DiT/dLLM models through techniques such as quantization, cache mechanism, and specific algorithmic methods.
Miscellany
  • Feel free to reach out via email or WeChat
Co-authors
0 total
Co-authors: 0 (list not available)