Hugging Face's logo
Fu-Yun Wang's picture
22 17 26

Fu-Yun Wang

wangfuyun
stablegravity's profile picture emadhanna's profile picture linjinbao666's profile picture
·
https://g-u-n.github.io

AI & ML interests

None yet

Recent Activity

reacted to their post with 🚀 about 1 month ago
PromptRL: Language Models as Co-Learners in Flow-Based Image Generation RL 🚀 We found two critical failure modes in flow-based RL: 1️⃣ Quality-Diversity Dilemma: High-quality models produce similar outputs, bottlenecking RL exploration 2️⃣ Prompt Linguistic Hacking: Models overfit to surface patterns—paraphrase the prompt and performance tanks Solution: **Jointly train LM + FM** — the LM dynamically generates semantically-consistent but diverse prompt variants 📊 Results: • GenEval: 0.97 • OCR accuracy: 0.98 • PickScore: 24.05 • 2×+ fewer rollouts than flow-only RL Paper: arxiv.org/abs/2602.01382 Code: github.com/G-U-N/UniRL #AI #TextToImage #ReinforcementLearning #Diffusion
authored a paper about 1 month ago
PromptRL: Prompt Matters in RL for Flow-Based Image Generation
posted an update about 1 month ago
PromptRL: Language Models as Co-Learners in Flow-Based Image Generation RL 🚀 We found two critical failure modes in flow-based RL: 1️⃣ Quality-Diversity Dilemma: High-quality models produce similar outputs, bottlenecking RL exploration 2️⃣ Prompt Linguistic Hacking: Models overfit to surface patterns—paraphrase the prompt and performance tanks Solution: **Jointly train LM + FM** — the LM dynamically generates semantically-consistent but diverse prompt variants 📊 Results: • GenEval: 0.97 • OCR accuracy: 0.98 • PickScore: 24.05 • 2×+ fewer rollouts than flow-only RL Paper: arxiv.org/abs/2602.01382 Code: github.com/G-U-N/UniRL #AI #TextToImage #ReinforcementLearning #Diffusion
View all activity

Organizations

Nanjing University's profile picture ZeroGPU Explorers's profile picture