Zhengyang Liang
Scholar

Zhengyang Liang

Google Scholar ID: 9IC8FBQAAAAJ
Singapore Management University
MultimodalComputer Vision
Citations & Impact
All-time
Citations
405
 
H-index
4
 
i10-index
4
 
Publications
9
 
Co-authors
3
list available
Resume (English only)
Academic Achievements
  • Paper 'Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Representation Learning' accepted by ACMMM 2025
  • Three papers accepted by CVPR 2025, including 'Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding' (Oral)
  • Paper 'Any Information Is Just Worth One Single Screenshot: Unifying Search With Visualized Information Retrieval' accepted by ACL 2025
  • Released Video-XL-2 model in June 2025
  • Honorable Mention, Mathematical Contest in Modeling (MCM), USA, 2023
  • Second Prize in National (First Prize in Beijing), China Undergraduate Mathematical Contest in Modeling, 2022
  • Published 'Self-Supervised Multi-Modal Knowledge Graph Contrastive Hashing for Cross-Modal Search' at AAAI 2023 as first student author