Awesome Multimodal

📄Papers 🧭Topics 🔥Trending 🗺️Map 🏆Leaderboards 🎓Learn 🤖Ask AI

⋯More

👥Authors 📚Reading Packs 📊Datasets 🛠️Tools 📰News 📝Blogs ✉️Newsletter 🎯Research Radar 🔖Saved

← authors · overview

Loading author…

Stay Updated

E-Mail Digest 🎯 Research Radar

Submit a paper · Privacy · Terms

© 2026 Awesome Papers.

Qingyi Si — most-cited papers & profile · Multimodal

← authors · overview

Qingyi Si

1 papers · 0 citations · 7 h-index

Huawei Technologies (United Kingdom)

Google Scholar ↗Semantic Scholar ↗OpenAlex ↗

Most-cited papers

Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection
2026

Top co-authors

Jinhu Fu · 1 Sen Su · 1 Shudong Zhang · 1 Yan Bai · 1 Yihang Lou · 1

Topics

Vision-Language Models Video-Language Benchmarks