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
Wenxuan Peng — most-cited papers & profile · Multimodal
← authors
·
overview
Wenxuan Peng
3
papers ·
1
citations
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples
2024 · 1 citations
Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes
2026
Panoptic Video Scene Graph Generation
2023
Topics
Image Generation
Image Restoration
Video Understanding
Segmentation
Vision-Language
Evaluation