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
Xinyu Cai — most-cited papers & profile · Multimodal
← authors
·
overview
Xinyu Cai
9
papers ·
7
citations ·
0
h-index
China University of Geosciences · Zhejiang University
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing
2026
HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding
2026
Ur-bench: A Benchmark For Multi-hop Reasoning Over Ultra-high-resolution Images
2025
Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback
2025
Top co-authors
Botian Shi
· 4
Yufan Shen
· 3
Licheng Wen
· 2
Nianchen Deng
· 2
Pinlong Cai
· 2
Siqi Li
· 2
Xuemeng Yang
· 2
Yu Qiao
· 2
Bin Fu
· 1
Daocheng Fu
· 1
Hairong Zhang
· 1
Hongbin Zhou
· 1
Topics
Benchmarks
Vision-Language Models
Embodied & Agents
Visual QA & Reasoning
Image-Text Retrieval
Audio-Visual