-
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Paper • 2508.20751 • Published • 89 -
CodeGoat24/UniGenBench-EvalModel-qwen-72b-v1
Image-to-Text • 73B • Updated • 5 -
CodeGoat24/UniGenBench-Eval-Images
Viewer • Updated • 762k • 3.08k • 2 -
CodeGoat24/UniGenBench
Updated • 141 • 1
SII-Yibin Wang
CodeGoat24
AI & ML interests
I'm part of Shanghai Innovation Institute, focusing on Multimodal RL and Generation.
Recent Activity
updated
a model
about 22 hours ago
CodeGoat24/UniGenBench-EvalModel-qwen-72b-v1
updated
a dataset
about 23 hours ago
CodeGoat24/UniGenBench-Eval-Images
updated
a collection
1 day ago
Pref-GRPO & UniGenBench
Organizations
-
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Paper • 2508.20751 • Published • 89 -
CodeGoat24/UniGenBench-EvalModel-qwen-72b-v1
Image-to-Text • 73B • Updated • 5 -
CodeGoat24/UniGenBench-Eval-Images
Viewer • Updated • 762k • 3.08k • 2 -
CodeGoat24/UniGenBench
Updated • 141 • 1
spaces
4
pinned
Running
2
UniGenBench Leaderboard (Chinese Long)
🏅
UniGenBench: a unified T2I generation benchmark.
pinned
Running
1
UniGenBench Leaderboard (Chinese)
🏅
UniGenBench: a unified T2I generation benchmark.
pinned
Running
2
UniGenBench Leaderboard (English Long)
🏅
UniGenBench: a unified T2I generation benchmark.
pinned
Running
3
UniGenBench Leaderboard (English)
🏅
UniGenBench: a unified T2I generation benchmark.
models
19
CodeGoat24/UniGenBench-EvalModel-qwen-72b-v1
Image-to-Text
•
73B
•
Updated
•
5
CodeGoat24/UnifiedReward-2.0-qwen-72b
Image-to-Text
•
73B
•
Updated
•
144
CodeGoat24/UnifiedReward-2.0-qwen-32b
33B
•
Updated
•
129
CodeGoat24/UnifiedReward-2.0-qwen-3b
4B
•
Updated
•
91
•
1
CodeGoat24/UnifiedReward-2.0-qwen-7b
8B
•
Updated
•
386
CodeGoat24/FLUX.1-dev-PrefGRPO
Text-to-Image
•
Updated
•
15
•
3
CodeGoat24/UnifiedReward-Think-7b
8B
•
Updated
•
11
•
10
CodeGoat24/UnifiedReward-Think-qwen-7b
8B
•
Updated
•
1.46k
•
3
CodeGoat24/T2V-Turbo
Updated
CodeGoat24/LLaVA-Video-7B-Qwen2-UnifiedReward-DPO
8B
•
Updated
•
5
datasets
15
CodeGoat24/UniGenBench-Eval-Images
Viewer
•
Updated
•
762k
•
3.08k
•
2
CodeGoat24/UniGenBench
Updated
•
141
•
1
CodeGoat24/UnifiedReward-2.0-T2X-score-data
Viewer
•
Updated
•
337k
•
192
CodeGoat24/VIDEOGEN
Viewer
•
Updated
•
50.9k
•
46
CodeGoat24/GENAI-BENCH
Viewer
•
Updated
•
27.8k
•
30
CodeGoat24/ShareGPTVideo-DPO
Viewer
•
Updated
•
101k
•
96
CodeGoat24/VideoFeedback
Viewer
•
Updated
•
73.2k
•
103
CodeGoat24/VideoDPO
Viewer
•
Updated
•
29k
•
106
CodeGoat24/OIP
Viewer
•
Updated
•
21.4k
•
105
CodeGoat24/LLaVA-Critic-113k
Preview
•
Updated
•
71