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
Pengfei Wan — most-cited papers & profile · Multimodal
← authors
·
overview
Pengfei Wan
16
papers ·
26
citations ·
22
h-index
OriginWater (China)
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping
2025 · 26 citations
SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder
2025
GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models
2025
Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control
2025
Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention
2025
DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers
2025
Top co-authors
Chang Liu
· 1
Fangyuan Kong
· 1
Haotian Wang
· 1
Henglin Liu
· 1
Jing Wang
· 1
Kun Gai
· 1
Letian Cheng
· 1
Nisha Huang
· 1
Qixun Wang
· 1
Qi Zhang
· 1
Ruizhe Chen
· 1
Tianrun Xu
· 1
Topics
Text-to-Image
Diffusion Models
Text-to-Video
Training & Sampling
Policy Gradient
RLHF & Alignment
Safe RL
Control
Manipulation
Multi-Robot