Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
22
17
26
Fu-Yun Wang
wangfuyun
Follow
LLL001's profile picture
llmpanda's profile picture
karanjakhar's profile picture
2899 followers
·
3 following
https://g-u-n.github.io
g-u-n
AI & ML interests
None yet
Recent Activity
authored
a paper
about 16 hours ago
PromptRL: Prompt Matters in RL for Flow-Based Image Generation
posted
an
update
about 19 hours 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
upvoted
an
article
about 22 hours ago
PromptRL: Prompt Matters in RL for Flow-Based Image Generation
View all activity
Organizations
wangfuyun
's models
11
Sort: Recently updated
wangfuyun/PrompRL
Updated
4 days ago
•
1
wangfuyun/kontext_1k3
21B
•
Updated
16 days ago
•
5
wangfuyun/consolver
Text-to-Image
•
Updated
Dec 22, 2025
•
29
•
1
wangfuyun/Diffusion-NPO
Text-to-Image
•
Updated
Nov 19, 2025
wangfuyun/PCM_Weights
Text-to-Image
•
Updated
Oct 30, 2024
•
20
•
99
wangfuyun/AnimateLCM-I2V
Image-to-Video
•
Updated
Oct 16, 2024
•
82
wangfuyun/AnimateLCM
Text-to-Video
•
Updated
Oct 16, 2024
•
10.5k
•
342
wangfuyun/Rectified-Diffusion
Text-to-Image
•
Updated
Oct 15, 2024
•
9
wangfuyun/Motion-I2V
Updated
Jul 11, 2024
•
3
wangfuyun/Be-Your-Outpainter
Updated
Jul 3, 2024
•
6
wangfuyun/AnimateLCM-SVD-xt
Image-to-Video
•
Updated
Feb 27, 2024
•
197