-
Unified Personalized Reward Model for Vision Generation
Paper • 2602.02380 • Published • 20 -
CodeGoat24/FLUX.2-klein-base-9B-UnifiedReward-Flex-lora
Text-to-Image • Updated • 305 • 14 -
CodeGoat24/Wan2.2-T2V-A14B-UnifiedReward-Flex-lora
Text-to-Video • Updated • 102 • 6 -
CodeGoat24/Wan2.1-T2V-14B-UnifiedReward-Flex-lora
Text-to-Video • Updated • 94 • 5
SII-Yibin Wang
CodeGoat24
AI & ML interests
I'm part of Shanghai Innovation Institute, focusing on Multimodal RL and Generation.
Recent Activity
updated
a Space
about 11 hours ago
CodeGoat24/UniGenBench_Leaderboard_Chinese_Long
updated
a Space
about 11 hours ago
CodeGoat24/UniGenBench_Leaderboard_Chinese
updated
a Space
about 11 hours ago
CodeGoat24/UniGenBench_Leaderboard_English_Long
Organizations
Pref-GRPO & UniGenBench
-
UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation
Paper • 2510.18701 • Published • 67 -
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Paper • 2508.20751 • Published • 89 -
CodeGoat24/UniGenBench-Eval-Images
Updated • 576 • 4 -
CodeGoat24/UniGenBench-EvalModel-qwen3vl-32b-v1
Image-Text-to-Text • 1.14M • Updated • 16
UnifiedReward Flex
-
Unified Personalized Reward Model for Vision Generation
Paper • 2602.02380 • Published • 20 -
CodeGoat24/FLUX.2-klein-base-9B-UnifiedReward-Flex-lora
Text-to-Image • Updated • 305 • 14 -
CodeGoat24/Wan2.2-T2V-A14B-UnifiedReward-Flex-lora
Text-to-Video • Updated • 102 • 6 -
CodeGoat24/Wan2.1-T2V-14B-UnifiedReward-Flex-lora
Text-to-Video • Updated • 94 • 5
Pref-GRPO & UniGenBench
-
UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation
Paper • 2510.18701 • Published • 67 -
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Paper • 2508.20751 • Published • 89 -
CodeGoat24/UniGenBench-Eval-Images
Updated • 576 • 4 -
CodeGoat24/UniGenBench-EvalModel-qwen3vl-32b-v1
Image-Text-to-Text • 1.14M • Updated • 16
spaces
4
pinned
Running
3
UniGenBench Leaderboard (Chinese Long)
🏅
UniGenBench: a unified T2I generation benchmark.
pinned
Running
3
UniGenBench Leaderboard (Chinese)
🏅
UniGenBench: a unified T2I generation benchmark.
pinned
Running
3
UniGenBench Leaderboard (English Long)
🏅
UniGenBench: a unified T2I generation benchmark.
pinned
Running
7
UniGenBench Leaderboard (English)
🏅
UniGenBench: a unified T2I generation benchmark.
models
44
CodeGoat24/Wan2.2-T2V-A14B-UnifiedReward-Flex-lora
Text-to-Video
•
Updated
•
102
•
6
CodeGoat24/UnifiedReward-Flex-qwen3vl-32b
1.14M
•
Updated
•
45
CodeGoat24/UnifiedReward-Flex-qwen3vl-2b
2B
•
Updated
•
42
CodeGoat24/UnifiedReward-Flex-qwen3vl-4b
4B
•
Updated
•
40
CodeGoat24/UnifiedReward-Flex-qwen3vl-8b
9B
•
Updated
•
439
CodeGoat24/FLUX.1-dev-UnifiedReward-Flex
Text-to-Image
•
Updated
•
29
CodeGoat24/Wan2.1-T2V-14B-UnifiedReward-Flex-lora
Text-to-Video
•
Updated
•
94
•
5
CodeGoat24/FLUX.2-klein-base-9B-UnifiedReward-Flex-lora
Text-to-Image
•
Updated
•
305
•
14
CodeGoat24/UnifiedReward-Think-qwen3vl-32b
1.14M
•
Updated
•
371
CodeGoat24/UniGenBench-EvalModel-qwen3vl-32b-v1
Image-Text-to-Text
•
1.14M
•
Updated
•
16
datasets
14
CodeGoat24/UniGenBench-Eval-Images
Updated
•
576
•
4
CodeGoat24/UnifiedReward-Flex-SFT-90K
Viewer
•
Updated
•
1.39M
•
122
•
2
CodeGoat24/UniGenBench
Updated
•
29
•
3
CodeGoat24/UnifiedReward-2.0-T2X-score-data
Viewer
•
Updated
•
337k
•
304
CodeGoat24/VIDEOGEN
Viewer
•
Updated
•
50.9k
•
12
CodeGoat24/ShareGPTVideo-DPO
Viewer
•
Updated
•
101k
•
73
CodeGoat24/VideoFeedback
Viewer
•
Updated
•
73.2k
•
78
CodeGoat24/VideoDPO
Viewer
•
Updated
•
29k
•
158
CodeGoat24/OIP
Viewer
•
Updated
•
21.4k
•
74
CodeGoat24/LLaVA-Critic-113k
Preview
•
Updated
•
153