Yifan Du
Scholar

Yifan Du

Google Scholar ID: YJf-45cAAAAJ
Renmin University of China
Vision Language ModelMLLM
Citations & Impact
All-time
Citations
8,451
 
H-index
10
 
i10-index
10
 
Publications
12
 
Co-authors
7
list available
Resume (English only)
Academic Achievements
  • Published 'Virgo: A Preliminary Exploration on Reproducing o1-like MLLM'
  • Published 'Exploring the Design Space of Visual Context Representation in Video MLLMs' (arXiv)
  • Published 'Towards Event-oriented Long Video Understanding' (arXiv)
  • Published 'What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning' (COLING 2025)
  • Published 'Evaluating Object Hallucination in Large Vision-Language Models' (EMNLP 2023)
  • Co-authored survey 'A Survey of Large Language Models'
  • Published 'Zero-shot Visual Question Answering with Language Model Feedback' (ACL 2023 Findings)
  • Published 'Learning to Imagine: Visually-Augmented Natural Language Generation' (ACL 2023)
  • Published survey 'A Survey of Vision-Language Pre-Trained Models' (IJCAI 2022)
  • Open-source project: Virgo (an MLLM with slow-thinking reasoning ability)
  • Open-source project: POPE (a benchmark for evaluating object hallucination in MLLMs)