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
Hang hua — most-cited papers & profile · Multimodal
← authors
·
overview
Hang hua
5
papers ·
1
citations ·
9
h-index
University of Rochester
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models
2024 · 1 citations
SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs
2026
DAVE: A VLM Vision Encoder For Document Understanding And Web Agents
2025
V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning
2024
FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity
2024
Top co-authors
Jiebo Luo
· 3
Chenliang Xu
· 2
Brandon Huang
· 1
Hangfeng He
· 1
Jianming Zhang
· 1
Jing Shi
· 1
Junling Wang
· 1
Konrad Schindler
· 1
Liangliang Cao
· 1
Li Mi
· 1
Lingzhi Zhang
· 1
Mattia Rigotti
· 1
Topics
Vision-Language Models
Benchmarks
Visual QA & Reasoning
Video-Language
Embodied & Agents
Instruction Tuning
Image-Text Retrieval