Yuanhuiyi Lyu
Scholar

Yuanhuiyi Lyu

Google Scholar ID: 6_lvla4AAAAJ
PhD Student, The Hong Kong University of Science and Technology (Guangzhou)
Visual GenerationUnified Model
Citations & Impact
All-time
Citations
481
 
H-index
13
 
i10-index
18
 
Publications
20
 
Co-authors
18
list available
Resume (English only)
Academic Achievements
  • Publications:
  • • 'Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation', arXiv, 2025
  • • 'RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning', ICML 2025
  • • 'UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All', CVPR 2024
  • • 'Image Anything: Towards Reasoning-coherent and Training-free Multi-modal Image Generation', arXiv, 2024
  • • 'Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities', ECCV 2024 (Oral)
  • • 'Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval', ICLR 2023
  • Awards:
  • • Outstanding Graduation Dissertation (<2%), Northeastern University, 2023
  • • Outstanding Students Scholarship, Northeastern University, 2020–2022
  • Service:
  • • Reviewer for CVPR, ECCV, ICCV, ICLR, ICML, NeurIPS, WACV, AAAI
  • • Reviewer for journals IJCV and TIP
  • Teaching:
  • • Teaching Assistant for Applied Statistics (UFUG2104), HKUST Guangzhou, Feb–Jun 2025
  • • Teaching Assistant for Red Bird Challenge Camp (RBCC), HKUST Guangzhou, Jul–Aug 2025