Awesome Multimodal
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
TianTian Geng — most-cited papers & profile · Multimodal
← authors
·
overview
TianTian Geng
1
papers ·
0
citations
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
When Text Hijacks Vision: Benchmarking and Mitigating Text Overlay-Induced Hallucination in Vision Language Models
2026
Top co-authors
Cui Yakun
· 1
Sirui Han
· 1
Xingqun Qi
· 1
Yike Guo
· 1
Yuyao Zhang
· 1
Topics
Vision-Language Models
Benchmarks
Video-Language
Visual QA & Reasoning