Shenghai Yuan (袁盛海)
Scholar

Shenghai Yuan (袁盛海)

Google Scholar ID: kcgdO0sAAAAJ
Peking University
Machine LearningComputer Vision
Citations & Impact
All-time
Citations
417
 
H-index
9
 
i10-index
9
 
Publications
16
 
Co-authors
7
list available
Publications
16 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • - Publications:
  • - OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation (NeurIPS D&B, 2025)
  • - Identity-Preserving Text-to-Video Generation by Frequency Decomposition (CVPR Highlight, 2025)
  • - ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation (NeurIPS D&B Spotlight, 2024)
  • - MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators (TPAMI, 2025)
  • - LHNetV2: A Balanced Low-cost Hybrid Network for Single Image Dehazing (TMM, 2024)
  • - LHNet: A Low-cost Hybrid Network for Single Image Dehazing (ACM MM, 2023)
  • - Patents:
  • - An acceleration system and method for deconvolution calculation in neural networks (CN202210582998.5 / CN114821262A)
  • - A cleaning device for exterior windows of high-rise buildings (CN201821848303.9 / CN209678371U)
  • - FPGA-based mixed-precision data frequency domain convolution acceleration method and system (CN201821848303.9 / CN209678371U)
  • - Awards:
  • - National Scholarship Award, PRC (2025)
  • - Pacemaker to Merit Student, Peking University (2025)
  • - National Scholarship Award, PRC (2023)
  • - National Scholarship Award, PRC (2022)
Research Experience
  • - Graduate student at the School of Electron and Computer Engineering, Peking University
  • - Involved in multiple research projects such as OpenS2V-Nexus, Identity-Preserving Text-to-Video Generation, etc.
Education
  • - Master of Computer Science and Technology, School of Electron and Computer Engineering, Peking University, advised by Prof. Li Yuan
  • - B. Eng in School of Computer Science and Technology, Guangdong University of Technology
Background
  • Research interests include but are not limited to video generation and multimodal large language models.
Miscellany
  • Personal interests and other information not provided.