Training Multimodal Reward Model Through Stable Reinforcement Learning
Yi-Fan Zhang
yifanzhang114
AI & ML interests
Yi-Fan Zhang presently is a forth-year PhD student at the State Key Laboratory of Pattern Recognition, University of Chinese Academy of Sciences, under the esteemed guidance of Prof. Tieniu Tan, is dedicated to spearheading robust and reliable deep learning systems and large pretrained models.
Recent Activity
upvoted
a
paper
3 days ago
Kwai Keye-VL 1.5 Technical Report
liked
a model
9 days ago
Kwai-Keye/Keye-VL-1_5-8B
updated
a dataset
12 days ago
yifanzhang114/MMPreferenceV
Organizations
The Next Step Forward in Multimodal LLM Alignment
-
yifanzhang114/MM-RLHF
Viewer • Updated • 16.3k • 216 • 11 -
yifanzhang114/MM-RLHF-RewardBench
Viewer • Updated • 170 • 180 • 3 -
yifanzhang114/MM-RLHF-Reward-7B-llava-ov-qwen
Image-Text-to-Text • 8B • Updated • 439 • 1 -
MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
Paper • 2502.10391 • Published • 35
Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
-
MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
Paper • 2408.13257 • Published • 27 -
yifanzhang114/MME-RealWorld
Preview • Updated • 900 • 19 -
yifanzhang114/MME-RealWorld-Base64
Viewer • Updated • 11.5k • 570 • 1 -
yifanzhang114/MME-RealWorld-CN-Lmms-eval
Viewer • Updated • 5.89k • 395 • 1
Training Multimodal Reward Model Through Stable Reinforcement Learning
The Next Step Forward in Multimodal LLM Alignment
-
yifanzhang114/MM-RLHF
Viewer • Updated • 16.3k • 216 • 11 -
yifanzhang114/MM-RLHF-RewardBench
Viewer • Updated • 170 • 180 • 3 -
yifanzhang114/MM-RLHF-Reward-7B-llava-ov-qwen
Image-Text-to-Text • 8B • Updated • 439 • 1 -
MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
Paper • 2502.10391 • Published • 35
Traing data and models of SliME
Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
-
MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
Paper • 2408.13257 • Published • 27 -
yifanzhang114/MME-RealWorld
Preview • Updated • 900 • 19 -
yifanzhang114/MME-RealWorld-Base64
Viewer • Updated • 11.5k • 570 • 1 -
yifanzhang114/MME-RealWorld-CN-Lmms-eval
Viewer • Updated • 5.89k • 395 • 1