Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
22
17
26
Fu-Yun Wang
wangfuyun
Follow
alam00's profile picture
bharatjadhav's profile picture
billionsmall'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 15 hours ago
PromptRL: Prompt Matters in RL for Flow-Based Image Generation
posted
an
update
about 18 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 21 hours ago
PromptRL: Prompt Matters in RL for Flow-Based Image Generation
View all activity
Organizations
wangfuyun
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a model
about 21 hours ago
wangfuyun/PrompRL
Updated
4 days ago
•
1
liked
a model
3 days ago
moonshotai/Kimi-K2.5
Image-Text-to-Text
•
Updated
about 18 hours ago
•
123k
•
•
1.59k
liked
2 models
about 1 month ago
Qwen/Qwen-Image-Layered
Image-Text-to-Image
•
Updated
Dec 19, 2025
•
16.7k
•
979
wangfuyun/consolver
Text-to-Image
•
Updated
Dec 22, 2025
•
29
•
1
liked
a dataset
6 months ago
UCSC-VLAA/GPT-Image-Edit-1.5M
Viewer
•
Updated
Aug 21, 2025
•
2.78M
•
5.08k
•
68
liked
2 datasets
7 months ago
BaiqiL/GenAI-Bench
Viewer
•
Updated
4 days ago
•
1.56k
•
225
•
23
lehduong/flux_generated
Viewer
•
Updated
Apr 20, 2025
•
1.75M
•
1
•
8
liked
a dataset
8 months ago
playgroundai/MJHQ-30K
Viewer
•
Updated
Jun 28, 2024
•
30k
•
714
•
62
liked
a dataset
9 months ago
jackyhate/text-to-image-2M
Viewer
•
Updated
Sep 22, 2024
•
649k
•
12k
•
147
liked
2 datasets
about 1 year ago
yerevann/coco-karpathy
Viewer
•
Updated
Oct 31, 2022
•
123k
•
1.64k
•
19
ILSVRC/imagenet-1k
Viewer
•
Updated
Sep 17, 2025
•
1.43M
•
110k
•
722
liked
a model
over 1 year ago
wangfuyun/Rectified-Diffusion
Text-to-Image
•
Updated
Oct 15, 2024
•
9
liked
3 datasets
over 1 year ago
nkp37/OpenVid-1M
Viewer
•
Updated
21 days ago
•
1.45M
•
44.6k
•
244
MuhammadHanif/Laion_aesthetics_5plus_1024_33M
Viewer
•
Updated
Apr 4, 2023
•
20.3M
•
83
•
23
jasonhuang23/laion2b_en_sd2.1base
Viewer
•
Updated
Jul 21, 2023
•
341M
•
124
•
9
liked
2 models
over 1 year ago
wangfuyun/Motion-I2V
Updated
Jul 11, 2024
•
3
wangfuyun/Be-Your-Outpainter
Updated
Jul 3, 2024
•
6
liked
a dataset
over 1 year ago
animelover/danbooru2022
Updated
Dec 4, 2023
•
322
•
153
liked
a Space
over 1 year ago
Runtime error
Featured
104
Phased Consistency Model PCM
🐠
104
Generate images from text prompts
liked
a model
over 1 year ago
wangfuyun/PCM_Weights
Text-to-Image
•
Updated
Oct 30, 2024
•
20
•
99
Load more