Scholar

Junjie Zhou (周俊杰)

Google Scholar ID: HE4gslQAAAAJ

PhD candidate, Beijing University of Posts and Telecommunications

Vision Language ModelMultimodal LearningMultimodal Retrieval

Citations & Impact

All-time

Citations

693

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

16 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Research Experience

Contributed to FlagEmbedding: Retrieval and retrieval-augmented LLMs
Contributed to MLVU: Multi-task Long Video Understanding Benchmark
Contributed to MegaPairs (ACL 2025 Oral): Massive data synthesis for universal multimodal retrieval
Contributed to OmniGen: Unified image generation model
Contributed to VISTA (ACL 2024): Visualized text embedding for universal multi-modal retrieval

Co-authors

6 total