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
Pengyuan Lyu — most-cited papers & profile · Multimodal
← authors
·
overview
Pengyuan Lyu
6
papers ·
0
citations ·
18
h-index
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
StrucTab: A Structured Optimization Framework for Table Parsing
2026
Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity
2026
MMTIT-Bench: A Multilingual and Multi-Scenario Benchmark with Cognition-Perception-Reasoning Guided Text-Image Machine Translation
2026
StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond
2024
Top co-authors
Gengluo Li
· 2
Xingyu Wan
· 2
Binghong Wu
· 1
Can Ma
· 1
Can Ma
· 1
Chengquan Zhang
· 1
Chengquan Zhang
· 1
Chengquan Zhang
· 1
Chengquan Zhang
· 1
Errui Ding
· 1
Gangyan Zeng
· 1
Guangming Lu
· 1
Topics
Vision-Language Models
Benchmarks
Visual QA & Reasoning
Image-Text Retrieval
Video-Language
Instruction Tuning